IP Library › Granted Patent US 12,412,072
Granted Patent B2
US 12,412,072 · App. 16/004,796 · Granted Sep 9, 2025

Characterizing activity in a recurrent artificial neural network

Inventors: Henry Markram (Lausanne, CH); Ran Levi (Aberdeen, GB); Kathryn Pamela Hess Bellwald (Aigle, CH)
Assignee: INAIT SA
G06N3/044G06N3/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,412,072
App. No.
16/004,796
Granted
Sep 9, 2025
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for characterizing activity in a recurrent artificial neural network. In one aspect, a method includes outputting digits from a recurrent artificial neural network, wherein each digit represents whether or not activity within a particular group of nodes in the recurrent artificial neural network comports with a respective pattern of activity.

Claims (54)

1. A computer-implemented method comprising:

training a functional state of a recurrent artificial neural network that includes two thousand nodes or more to propagate an input according to a learned signal flow within the recurrent artificial neural network until processing of the input reaches a predefined end and the recurrent artificial neural network returns to a state in which only background or no signal transmission activity occurs, the training comprising:

structuring the recurrent artificial neural network to obtain a trained recurrent artificial neural network, the structuring comprising:

reading a plurality of digits output from the recurrent artificial neural network, wherein each digit represents whether or not activity within a particular group of nodes in the recurrent artificial neural network comports with a respective pattern of activity; and

evolving a structure of the recurrent artificial neural network, wherein evolving the structure of the recurrent artificial neural network comprises:

characterizing a complexity of each pattern of signal transmission activity in the structure, wherein the complexity is measured based on simplex counts or Betti numbers of the pattern,

using the characterization as an indication of whether the structure has optimized a reward, and

iteratively evolving the structure if the reward has not been optimized;

processing the input by the trained recurrent artificial neural network, the input comprising a stream of video or audio data;

monitoring complexities of patterns of signal transmission activity that occur between three or more nodes in the trained recurrent artificial neural network in response to the processing of the input, the monitoring comprising, during the processing of the input:

outputting, by the trained recurrent artificial neural network, a second plurality of digits, wherein a value of each digit in the second plurality of digits represents whether or not signal transmission activity that occurs between the three or more nodes in the trained recurrent artificial neural network in response to the processing of the input comports with a respective pattern of signal transmission activity, regardless of a location at which the respective pattern of signal transmission activity occurs in the trained recurrent artificial neural network, wherein the second plurality of digits enables an isomorphic topological reconstruction of a graph of the trained recurrent artificial neural network;

determining the complexity of each pattern of signal transmission activity;

identifying a time at which an object or sound is recognized in the stream of video or audio data, comprising identifying, based on the complexity of each pattern of signal transmission activity, a distinguishable level of complexity of the signal transmission activity, wherein the distinguishable level of complexity comprises an upward deviation, downward deviation, or change of complexity from a predetermined threshold level of complexity;

outputting, at the identified time and before the trained recurrent artificial neural network completes the processing of the input to reach the predefined end and return to the state in which only background or no signal transmission activity occurs, the patterns of signal transmission activity that have the distinguishable level of complexity; and

transmitting, encrypting, or storing the output patterns of signal transmission activity that have the distinguishable level of complexity; and

allowing the trained recurrent artificial neural network to return to the state in which only background or no signal transmission activity occurs.

2. The method of claim 1 , further comprising determining whether or not each group of nodes comports with the respective pattern of signal transmission activity by identifying clique patterns of signal transmission activity of the trained recurrent artificial neural network.

3. The method of claim 2 , wherein the method further comprises defining a plurality of windows of time during which the signal transmission activity of the trained recurrent artificial neural network is responsive to the input into the trained recurrent artificial neural network, wherein each digit represents whether or not the signal transmission activity within the group of nodes comports with a respective clique pattern of signal transmission activity during a respective window of the plurality of windows.

4. The method of claim 3 , wherein the method further comprises identifying a first window of time within the plurality of windows of time based on an increased likelihood of the clique patterns being identified during the first window of time when compared to other windows of the plurality of windows of time.

5. The method of claim 1 , wherein each of the respective patterns of signal transmission activity encloses a cavity.

6. The method of claim 2 , wherein identifying cliques comprises discarding or ignoring cliques that are present in other cliques.

7. The method of claim 1 , wherein each of the digits is output from a reader node coupled to a collection of nodes in the trained recurrent artificial neural network, wherein the reader nodes indicate if signal transmission activity of the nodes in the collection comports with a particular pattern of signal transmission activity.

8. The method of claim 1 , further comprising transmitting or storing a quantity of the digits, wherein transmitting or storing a quantity of the digits comprises:

transmitting or storing digits associated with patterns of signal transmission activity having a complexity higher than the predetermined threshold level; and

discarding or ignoring digits associated with patterns of signal transmission activity having a complexity lower than the predetermined threshold level.

9. The method of claim 1 , wherein times at which the patterns of signal transmission activity that have the distinguishable level of complexity occur provide a classification as to whether data in the data stream at the times satisfies object or sound recognition criteria.

10. A data transmitter or data storage device comprising an encoder comprising one or more computers operable to perform operations, the operations comprising:

training a functional state of a recurrent artificial neural network that includes two thousand nodes or more to propagate an input according to a learned signal flow within the recurrent artificial neural network until processing of the input reaches a predefined end and the recurrent artificial neural network returns to a state in which only background or no signal transmission activity occurs, the training comprising:

structuring the recurrent artificial neural network to obtain a trained recurrent artificial neural network, the structuring comprising:

reading a plurality of digits output from the recurrent artificial neural network, wherein each digit represents whether or not activity within a particular group of nodes in the recurrent artificial neural network comports with a respective pattern of activity; and

evolving a structure of the recurrent artificial neural network, wherein evolving the structure of the recurrent artificial neural network comprises:

characterizing a complexity of each pattern of signal transmission activity in the structure, wherein the complexity is measured based on simplex counts or Betti numbers of the pattern,

using the characterization as an indication of whether the structure has optimized a reward, and

iteratively evolving the structure if the reward has not been optimized;

encoding a result of processing of an input by the trained recurrent artificial neural network, the input comprising a stream of video or audio data, wherein encoding the result of processing comprises:

processing the input by the trained recurrent artificial neural network;

monitoring complexities of patterns of signal transmission activity that occur between three or more nodes in the trained recurrent artificial neural network in response to the processing of the input, the monitoring comprising, during the processing of the input:

outputting, by the trained recurrent artificial neural network, a second plurality of digits from the trained recurrent artificial neural network, wherein a value of each digit in the second plurality of digits represents whether or not signal transmission activity that occurs between the three or more nodes in the trained recurrent artificial neural network in response to the processing of the input comports with a respective pattern of signal transmission activity, regardless of a location at which the respective pattern of signal transmission activity occurs in the trained recurrent artificial neural network, wherein the second plurality of digits enables an isomorphic topological reconstruction of a graph of the trained recurrent artificial neural network,

determining the complexity of each pattern of signal transmission activity;

identifying a time at which an object or sound is recognized in the stream of video or audio data, comprising

identifying, based on the complexity of each pattern of signal transmission activity, a distinguishable level of complexity of the signal transmission activity, wherein the distinguishable level of signal transmission activity comprises an upward deviation, downward deviation, or change of complexity from a predetermined threshold level of complexity;

outputting, at the identified time and before the trained recurrent artificial neural network completes the processing of the input to reach the predefined end and return to the state in which only background or no signal transmission activity occurs, the result of processing of the input, the result comprising the patterns of signal transmission activity that have the distinguishable level of complexity; and

transmitting, encrypting, or storing the output patterns of signal transmission activity that have the distinguishable level of complexity; and

allowing the trained recurrent artificial neural network to return to the state in which only background or no signal transmission activity occurs.

11. The encoder of claim 10 , wherein the operations further comprise determining whether or not each group of nodes comports with the respective pattern of signal transmission activity by identifying clique patterns of signal transmission activity of the trained recurrent artificial neural network.

12. The encoder of claim 11 , wherein the operations further comprise defining a plurality of windows of time during which the signal transmission activity of the trained recurrent artificial neural network is responsive to the input into the trained recurrent artificial neural network, wherein each digit represents whether or not signal transmission activity within the group of nodes comports with a respective clique pattern of signal transmission activity during a respective window of the plurality of windows.

13. The encoder of claim 12 , wherein the operations further comprise identifying a first window of time within the plurality of windows of time based on an increased likelihood of the clique patterns being identified during the first window of time when compared to other windows of the plurality of windows of time.

14. The encoder of claim 10 , wherein the respective patterns of signal transmission activity enclose cavities.

15. The encoder of claim 10 , wherein each of the digits is output from a reader node coupled to a collection of nodes in the trained recurrent artificial neural network, wherein the reader nodes indicate if signal transmission activity of the nodes in the collection comports with a particular pattern of signal transmission activity.

16. The encoder of claim 10 , further comprising transmitting or storing a quantity of the digits, wherein transmitting or storing a quantity of the digits comprises:

transmitting or storing digits associated with patterns of signal transmission activity having a complexity higher than the predetermined threshold level; and

discarding or ignoring digits associated with patterns of signal transmission activity having a complexity lower than the predetermined threshold level.

17. The encoder of claim 10 , wherein the encoder is a video encoder.

18. The encoder of claim 10 , wherein times at which the patterns of signal transmission activity that have the distinguishable level of complexity occur provide a classification as to whether data in the data stream at the times satisfies object or sound recognition criteria.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 26, 2018
From: MARKRAM, HENRY; LEVI, RAN; HESS BELLWALD, KATHRYN PAMELA
To: INAIT SA
Reel/Frame 046474/0693 →
Continuity (1)
Related Publication 20190378000A1 · Dec 12, 2019
References Cited (400)
US 5822742A · Alkon et al. · 1998 [cited by applicant]
US 7321882B2 · Herbert · 2008 [cited by applicant]
US 7412426B2 · Hercus · 2008 [cited by applicant]
US 8818923B1 · Hoffmann · 2014 [cited by applicant]
US 9336239B1 · Hoffmann et al. · 2016 [cited by applicant]
US 9558442B2 · Canoy et al. · 2017 [cited by applicant]
US 9785886B1 · Andoni et al. · 2017 [cited by applicant]
US 9875440B1 · Lamport · 2018 [cited by applicant]
US 10019506B1 · Li et al. · 2018 [cited by applicant]
US 10153806B1 · Petre et al. · 2018 [cited by applicant]
US 10417558B1 · Bauer et al. · 2019 [cited by applicant]
US 10510000B1 · Lamport · 2019 [cited by applicant]
US 10621364B1 · El Defrawy · 2020 [cited by applicant]
US 10628486B2 · Chu et al. · 2020 [cited by applicant]
US 10650047B2 · Yanagisawa · 2020 [cited by applicant]
US 10885020B1 · Ablitt · 2021 [cited by applicant]
US 10922510B2 · Tscherepanow et al. · 2021 [cited by applicant]
US 11195038B2 · Nunn et al. · 2021 [cited by applicant]
US 11218498B2 · Hajimirsadeghi et al. · 2022 [cited by applicant]
US 11250326B1 · Ko et al. · 2022 [cited by applicant]
US 11278413B1 · Lang · 2022 [cited by applicant]
US 11569978B2 · Hess et al. · 2023 [cited by applicant]
US 11580401B2 · Markram et al. · 2023 [cited by applicant]
US 11615285B2 · Reimann et al. · 2023 [cited by applicant]
US 11651210B2 · Henry et al. · 2023 [cited by applicant]
US 11652603B2 · Markram et al. · 2023 [cited by applicant]
US 11663478B2 · Markram et al. · 2023 [cited by applicant]
US 11797827B2 · Markram et al. · 2023 [cited by applicant]
US 11816553B2 · Markram et al. · 2023 [cited by applicant]
US 11893471B2 · Markram et al. · 2024 [cited by applicant]
US 11972343B2 · Markram et al. · 2024 [cited by applicant]
US 12020157B2 · Markram et al. · 2024 [cited by applicant]
US 12113891B2 · Hess Bellwald et al. · 2024 [cited by applicant]
US 12147904B2 · Markram et al. · 2024 [cited by applicant]
US 12154023B2 · Markram et al. · 2024 [cited by applicant]
US 20030140020A1 · Chen et al. · 2003 [cited by applicant]
US 20040015459A1 · Herbert · 2004 [cited by applicant]
US 20060112028A1 · Xiao et al. · 2006 [cited by applicant]
US 20060184471A1 · Minamino et al. · 2006 [cited by applicant]
US 20080152217A1 · Greer · 2008 [cited by applicant]
US 20080267188A1 · Furber et al. · 2008 [cited by applicant]
US 20090006060A1 · Rhodes · 2009 [cited by examiner]
US 20090012581A1 · Rhodes · 2009 [cited by applicant]
US 20090187736A1 · Raichelgauz et al. · 2009 [cited by applicant]
US 20140156901A1 · Raichelgauz et al. · 2014 [cited by applicant]
US 20150058352A1 · Brand · 2015 [cited by applicant]
US 20150206049A1 · Canoy et al. · 2015 [cited by applicant]
US 20150280906A1 · Shany et al. · 2015 [cited by applicant]
US 20150310303A1 · Andreopoulos et al. · 2015 [cited by applicant]
US 20150347870A1 · Andreopoulos et al. · 2015 [cited by applicant]
US 20150363689A1 · Henry et al. · 2015 [cited by applicant]
US 20150371132A1 · Gemello et al. · 2015 [cited by applicant]
US 20160048756A1 · Hall et al. · 2016 [cited by applicant]
US 20160350648A1 · Gilad-Bachrach et al. · 2016 [cited by applicant]
US 20170024661A1 · Hunsberger et al. · 2017 [cited by applicant]
US 20170124452A1 · Tucker et al. · 2017 [cited by applicant]
US 20170139759A1 · Bandara · 2017 [cited by examiner]
US 20170213131A1 · Hammond et al. · 2017 [cited by applicant]
US 20170229117A1 · van der Made et al. · 2017 [cited by applicant]
US 20170249536A1 · Hillar et al. · 2017 [cited by applicant]
US 20180005111A1 · Chaudhari et al. · 2018 [cited by applicant]
US 20180018553A1 · Bach et al. · 2018 [cited by applicant]
US 20180053108A1 · Olabiyi et al. · 2018 [cited by applicant]
US 20180053114A1 · Adjaoute · 2018 [cited by applicant]
US 20180082171A1 · Merity et al. · 2018 [cited by applicant]
US 20180107922A1 · Paul et al. · 2018 [cited by applicant]
US 20180136912A1 · Venkataramani et al. · 2018 [cited by applicant]
US 20180157973A1 · El-Yaniv et al. · 2018 [cited by applicant]
US 20180165547A1 · Huang et al. · 2018 [cited by applicant]
US 20180197069A1 · Reimann et al. · 2018 [cited by applicant]
US 20180197076A1 · Paik et al. · 2018 [cited by applicant]
US 20180247198A1 · Vasudevan et al. · 2018 [cited by applicant]
US 20180336453A1 · Merity et al. · 2018 [cited by applicant]
US 20180373985A1 · Yang et al. · 2018 [cited by applicant]
US 20190012574A1 · Anthony et al. · 2019 [cited by applicant]
US 20190036678A1 · Ahmed · 2019 [cited by applicant]
US 20190042988A1 · Brown et al. · 2019 [cited by applicant]
US 20190044916A1 · Jones · 2019 [cited by applicant]
US 20190050726A1 · Azaria et al. · 2019 [cited by applicant]
US 20190122096A1 · Husain · 2019 [cited by applicant]
US 20190122140A1 · Sen · 2019 [cited by applicant]
US 20190171187A1 · Cella et al. · 2019 [cited by applicant]
US 20190171929A1 · Abadi et al. · 2019 [cited by applicant]
US 20190180187A1 · Rawal et al. · 2019 [cited by applicant]
US 20190197410A1 · Berry, II · 2019 [cited by applicant]
US 20190228300A1 · Cao et al. · 2019 [cited by applicant]
US 20190244348A1 · Buckler et al. · 2019 [cited by applicant]
US 20190265950A1 · Heeger et al. · 2019 [cited by applicant]
US 20190266246A1 · Wang et al. · 2019 [cited by applicant]
US 20190286074A1 · Hoffmann · 2019 [cited by applicant]
US 20190304568A1 · Wei et al. · 2019 [cited by applicant]
US 20190312898A1 · Verma et al. · 2019 [cited by applicant]
US 20190335192A1 · Otto · 2019 [cited by examiner]
US 20190354846A1 · Mellempudi et al. · 2019 [cited by applicant]
US 20190370647A1 · Doshi et al. · 2019 [cited by applicant]
US 20190377976A1 · Markram et al. · 2019 [cited by applicant]
US 20190377999A1 · Markram et al. · 2019 [cited by applicant]
US 20190378007A1 · Markram et al. · 2019 [cited by applicant]
US 20190378008A1 · Markram et al. · 2019 [cited by applicant]
US 20190392303A1 · Cherubini et al. · 2019 [cited by applicant]
US 20200011668A1 · Derhy et al. · 2020 [cited by applicant]
US 20200012927A1 · Raichelgauz et al. · 2020 [cited by applicant]
US 20200098135A1 · Ganjineh et al. · 2020 [cited by applicant]
US 20200117690A1 · Tran · 2020 [cited by applicant]
US 20200126126A1 · Briancon et al. · 2020 [cited by applicant]
US 20200134016A1 · Cao et al. · 2020 [cited by applicant]
US 20200184055A1 · Storm et al. · 2020 [cited by applicant]
US 20200210764A1 · Hamedi et al. · 2020 [cited by applicant]
US 20200228336A1 · Streit · 2020 [cited by applicant]
US 20200242444A1 · Zhang et al. · 2020 [cited by applicant]
US 20200285944A1 · Lee et al. · 2020 [cited by applicant]
US 20200302297A1 · Jaganathan et al. · 2020 [cited by applicant]
US 20200304284A1 · Markram et al. · 2020 [cited by applicant]
US 20200304285A1 · Hess et al. · 2020 [cited by applicant]
US 20200310400A1 · Jha et al. · 2020 [cited by applicant]
US 20200367810A1 · Shouldice et al. · 2020 [cited by applicant]
US 20200380335A1 · Neznal · 2020 [cited by applicant]
US 20200402497A1 · Semonov et al. · 2020 [cited by applicant]
US 20210027163A1 · Baker · 2021 [cited by applicant]
US 20210049441A1 · Bronstein · 2021 [cited by applicant]
US 20210049446A1 · Gurumurthi et al. · 2021 [cited by applicant]
US 20210058547A1 · Puttamalla et al. · 2021 [cited by applicant]
US 20210097578A1 · Holmes et al. · 2021 [cited by applicant]
US 20210110115A1 · Hermann et al. · 2021 [cited by applicant]
US 20210182604A1 · Anthony et al. · 2021 [cited by applicant]
US 20210182653A1 · Markram et al. · 2021 [cited by applicant]
US 20210182654A1 · Markram et al. · 2021 [cited by applicant]
US 20210182655A1 · Markram et al. · 2021 [cited by applicant]
US 20210182657A1 · Markram et al. · 2021 [cited by applicant]
US 20210182681A1 · Markram et al. · 2021 [cited by applicant]
US 20210271319A1 · Lussier et al. · 2021 [cited by applicant]
US 20210319098A1 · Pogorelik et al. · 2021 [cited by applicant]
US 20210338007A1 · Choi et al. · 2021 [cited by applicant]
US 20210398621A1 · Stojevic et al. · 2021 [cited by applicant]
US 20220005332A1 · Metzler et al. · 2022 [cited by applicant]
US 20220012877A1 · Buckler et al. · 2022 [cited by applicant]
US 20220147760A1 · Dutta et al. · 2022 [cited by applicant]
US 20220148454A1 · Jaramaz et al. · 2022 [cited by applicant]
US 20220157436A1 · Harley et al. · 2022 [cited by applicant]
US 20220187847A1 · Cella et al. · 2022 [cited by applicant]
US 20220197306A1 · Cella et al. · 2022 [cited by applicant]
US 20220261593A1 · Yu et al. · 2022 [cited by applicant]
US 20220269346A1 · Hussami et al. · 2022 [cited by applicant]
US 20230019839A1 · Markram · 2023 [cited by applicant]
US 20230024925A1 · Markram et al. · 2023 [cited by applicant]
US 20230028511A1 · Markram et al. · 2023 [cited by applicant]
US 20230085384A1 · Lütgehetmann et al. · 2023 [cited by applicant]
US 20230171086A1 · Hess et al. · 2023 [cited by applicant]
US 20230297808A1 · Reimann et al. · 2023 [cited by applicant]
US 20230316077A1 · Henry et al. · 2023 [cited by applicant]
US 20230351196A1 · Markram et al. · 2023 [cited by applicant]
US 20230370244A1 · Markram et al. · 2023 [cited by applicant]
US 20240046077A1 · Markram et al. · 2024 [cited by applicant]
US 20240111994A1 · Markram et al. · 2024 [cited by applicant]
US 20240176985A1 · Markram et al. · 2024 [cited by applicant]
US 20240362480A1 · Markram et al. · 2024 [cited by applicant]
US 20240386265A1 · Markram et al. · 2024 [cited by applicant]
US 20250070956A1 · Hess Bellwald et al. · 2025 [cited by applicant]
US 20250117628A1 · Markram et al. · 2025 [cited by applicant]
CN 101669130 · 2010 [cited by applicant]
CN 101719908A · 2010 [cited by applicant]
CN 102859538 · 2013 [cited by applicant]
CN 103988203 · 2014 [cited by applicant]
CN 104318304 · 2015 [cited by applicant]
CN 104335219 · 2015 [cited by applicant]
CN 105095966 · 2015 [cited by applicant]
CN 105787561A · 2016 [cited by applicant]
CN 106156845 · 2016 [cited by applicant]
CN 107247989 · 2017 [cited by applicant]
CN 107423814 · 2017 [cited by applicant]
CN 107743630A · 2018 [cited by applicant]
CN 107844830 · 2018 [cited by applicant]
CN 108348750 · 2018 [cited by applicant]
CN 112567388 · 2021 [cited by applicant]
CN 112567389 · 2021 [cited by applicant]
EP 1283496 · 2003 [cited by applicant]
EP 3340121 · 2018 [cited by applicant]
EP 3803707 · 2021 [cited by applicant]
EP 3803708 · 2021 [cited by applicant]
KR 20210008418 · 2021 [cited by applicant]
KR 20210008419 · 2021 [cited by applicant]
TW 201437945 · 2014 [cited by applicant]
TW 201535277 · 2015 [cited by applicant]
TW 201725519 · 2017 [cited by applicant]
TW I608429 · 2017 [cited by applicant]
TW 201928789 · 2019 [cited by applicant]
TW 201935326 · 2019 [cited by applicant]
TW 201937392 · 2019 [cited by applicant]
WO WO2007137047 · 2007 [cited by applicant]
WO WO2016206765 · 2016 [cited by applicant]
WO WO2017083399 · 2017 [cited by applicant]
WO WO2017197375 · 2017 [cited by applicant]
WO WO2017200971 · 2017 [cited by applicant]
WO WO2018058426 · 2018 [cited by applicant]
WO WO2018175400 · 2018 [cited by applicant]
WO WO2019238522 · 2019 [cited by applicant]
WO WO2019238523 · 2019 [cited by applicant]
WO WO2020187676 · 2020 [cited by applicant]
WO WO2020187694 · 2020 [cited by applicant]
WO WO2021116071 · 2021 [cited by applicant]
WO WO2021116075 · 2021 [cited by applicant]
WO WO2021116140 · 2021 [cited by applicant]
WO WO2021116147 · 2021 [cited by applicant]
WO WO2021116250 · 2021 [cited by applicant]
WO WO2021116379 · 2021 [cited by applicant]
WO WO2021116402 · 2021 [cited by applicant]
WO WO2021116404 · 2021 [cited by applicant]
WO WO2021116407 · 2021 [cited by applicant]
Blanco et al. “A genetic algorithm to obtain the optimal recurrent neural network.” International Journal of Approximate Reasoning 23 (2000) 67-83 (Year: 2000). [cited by examiner]
Lee et al. “Detecting highly overlapping community structure by greedy clique expansion,” arXiv preprint (arXiv:1002.1827v2), 2010, 10 pages (Year: 2010). [cited by examiner]
Dlotko et al. “Topological analysis of the connectome of digital reconstructions of neural microcircuits,” arXiv preprint, 2016, 28 pages (IDS Oct. 4, 2019, doc. 2) (Year: 2016). [cited by examiner]
Zhang et al., “Ternary weight networks,” arXiv preprint (arXiv:1605.04711v2), 2016, 5 pages (Year: 2016). [cited by examiner]
Masulli et al. The topology of the directed clique complex as a network invariant. Springerplus. 2016;5:388. Published Mar. 31, 2016. 12 pages. (Year: 2016). [cited by examiner]
Paweł Dłotko, “Directed clique topology” (slides are titled “Directed Complexes”), May 11, 2017, BIRS, Topological Methods in Brain Network Analysis (17w5043), Accessed from http://www.birs.ca/events/2017/5-day-workshop… [cited by examiner]
TW Office Action in Taiwanese Appln. No. 108119813, dated Jun. 29, 2020, 17 pages (with machine translation). [cited by applicant]
Dlotko et al., “Topological analysis of the connectome of digital reconstructions of neural microcircuits,” arXiv preprint, 2016, 28 pages. [cited by applicant]
Paugam-Moisy et al, “Delay learning and polychronization for reservoir computing,” Neurocomputing, Mar. 2008, 71(7-9):1143-1158. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/064593, dated Sep. 6, 2019, 18 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/064740, dated Sep. 6, 2019, 18 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/064741, dated Sep. 6, 2019, 16 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/064773, dated Sep. 6, 2019, 17 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/064776, dated Sep. 6, 2019, 17 pages. [cited by applicant]
Reimann et al, “Cliques of Neurons Bound into Cavities Provide a Missing Link between Structure and Function,” Frontiers in Computational Neuroscience, Jun. 2017, 11:48:16 pages. [cited by applicant]
Sun et al, “Runtime detection of activated polychronous neuronal group towards its spatiotemporal analysis,” 2015 International Joint Conference on Neural Networks, Jul. 2015, 1-8. [cited by applicant]
Woodward & Ikegami, “A Reservoir Computing approach to Image Classification using Coupled Echo State and Back-Propagation Neural Networks,” International conference image and vision computing, Auckland, New Zealand, Nov… [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/064741, dated Dec. 24, 2020, 9 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/064773, dated Dec. 24, 2020, 11 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/064776, dated Dec. 24, 2020, 11 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/064740, dated Dec. 24, 2020, 13 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/064593, dated Dec. 24, 2020, 11 pages. [cited by applicant]
Abbas et al., “Artificial Intelligence Conquering the next frontier of the digital world,” Research Gate, Dec. 17, 2017, 15 pages. [cited by applicant]
Aharoni et al. “Eigenvalues and homology of flag complexes and vector representations of graphs,” Geom. Funct. Anal., Jul. 28, 2005, 15:555-566. [cited by applicant]
Angeli, “Symmetric functions for fast image retrieval with persistent homology,” Math Meth Appl Sci., Apr. 24, 2018, 41:9567-9577. [cited by applicant]
Bale et al., “Efficient population coding of naturalistic whisker motion in the ventro-posterior medial thalamus based on precise spike timing,” Front. Neural Circuits, Sep. 25, 2015, 9: 1-14. [cited by applicant]
Bassett et al., “Network Neuroscience,” Network Neuroscience, Nat. Neurosci., Mar. 20, 2017, 20:353-364. [cited by applicant]
Bauer et al., “PHAT—Persistent Homology Algorithms Toolbox,” J. Symb. Comput., Jan. 1, 2017, 78: 76-90. [cited by applicant]
Bergomi et al., “Topological Graph persistence,” Mathematics, Jul. 20, 2017, pp. 1-15. [cited by applicant]
Bienenstock et al., “A model of neocortex,” Network Comput. Neural Syst., Jul. 27, 1994, 6:179-224. [cited by applicant]
Brody et al., “Correlations without synchrony,” Neural Comput. 11, Oct. 1, 1999, 11:1537-1551. [cited by applicant]
Bullmore et al., “Complex brain networks: graph theoretical analysis of structural and functional systems,” Nat. Rev. Neurosci., Mar. 10, 2009, 10:186-198. [cited by applicant]
Chella et al., “Representational Issues in the Debate on the Standard Model of the Mind, ”Association for the Advancement of Artificial Intelligence, Nov. 12, 2017, pp. 1-6. [cited by applicant]
Chklovskii et al., “Cortical rewiring and information storage,” Nature, Oct. 14, 2004, 431:782-788. [cited by applicant]
Choi et al., “A Survey of Binary Similarity and distance measures,” Systemic, Cybernetics, and Informatics, Jan. 8, 2010, 8:43-48. [cited by applicant]
Choudhary, “Approximation algorithms for Vietoris-Rips and Čech filtrations,” Doctoral Thesis of Computer Science, Faculty of Mathematics and Computer Science, Heidelberg University, Dec. 14, 2017, 140 pages. [cited by applicant]
Courtney et al., “Dense Power-law Networks and Simplicial Complexes,” ArXiv, Apr. 23, 2018, pp. 1-16. [cited by applicant]
Crawford et al., “A theory on the role of π-electrons of docosahexaenoic acid in brain function: The six methylene-interrupted double bonds and the precision of neural signaling,” Oilseeds & fats Crops and Lipids, May 2… [cited by applicant]
Davydov et al., “Neural Network Structures: Current and Future States,” Research Gate, Feb. 2, 2018, pp. 1-6. [cited by applicant]
Engel et al., “Temporal binding and the neural correlates of sensory awareness,” Trends Cogn. Sci., Jan. 1, 2001, 5: 16-25. [cited by applicant]
Erdős et al., “On the evolution of random graphs,” Publ. Math. Inst. Hung. Acad. Sci., Jan. 1960, 17-60. [cited by applicant]
Github.com [online] “pytorch-tutorial/tutorials/03-advanced/image_captioning/,” Oct. 2007, retrieved on Jan. 21, 2020, retrieved from UR: <https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/03-advanced/ima… [cited by applicant]
Giusti et al., “Clique topology reveals intrinsic geometric structure in neural correlations,” Proc. Natl. Acad. Sci. U.S.A., Apr. 28, 2015, 112: 13455-13460. [cited by applicant]
Gong, “Evolution to a small-world network with chaotic units,” Europhysics Letters (EPL), Jul. 15, 2004, 67:328-333. [cited by applicant]
Harris et al. “The neocortical circuit: themes and variations,” Nat. Neurosci., Jan. 27, 2015, 18:170-181. [cited by applicant]
Hastings et al., “Challenges in the analysis of complex systems: introduction and overview,” The European Physical Journal Special Topics, Dec. 28, 2017, 226:3185-3197. [cited by applicant]
Haun et al., “Conscious Perception as Integrated Information Patterns in Human Electrocorticography,” eNeuro: Cognition and Behavior, Sep. 19, 2017, 4:2-18. [cited by applicant]
Hebb, “The Organization of Behavior: A Neuropsychological Theory,” New York, NY: Wiley & Sons, 1949, pp. 1-365. [cited by applicant]
Holtmaat et al., “Experience-dependent structural synaptic plasticity in the mammalian brain, ” Nat. Rev. Neurosci., Sep. 10, 2009, 10: 647-658. [cited by applicant]
Ivancevic et al., “Tensor-Centric Warfare II: Entropic Uncertainty Modeling,” Intelligent Control and Automation, May 30, 2018, 9:30-51. [cited by applicant]
Judge, “Prefix “Re-Congition” as prelude to fixing sustainability—“pro” vs. “con”? Speculative review of missing emphasis potentially vital for psychosocial balance,” Research Gate, Jul. 16, 2017, pp. 1-22. [cited by applicant]
Knoblauch et al., “Memory capacities for synaptic and structural plasticity,” Neural Comput., Feb. 2010, 22:289-341. [cited by applicant]
Kulakov, “Features of a Simple Psychophysiological Reaction,” Human Physiology, Jun. 15, 2017, 44:412-417. [cited by applicant]
Latora et al., “Efficient behavior of small-world networks,” Phys. Rev. Lett., Oct. 17, 2001, 87:1-4. [cited by applicant]
Le Be et al., “Spontaneous and evoked synaptic rewiring in the neonatal neocortex,” Proc. Natl. Acad. Sci. U.S.A., Aug. 29, 2006 103:13214-13219. [cited by applicant]
Levi, “A short course on Algebraic topology geared towards applications to Neuroscience,” University of Aberdeen, Jul. 18, 2017, pp. 1-14. [cited by applicant]
Luczak et al., “Packetbased communication in the cortex,” Nat. Rev. Neurosci., Oct. 28, 2015, 16:745-755. [cited by applicant]
Markram et al., “Reconstruction and simulation of neocortical microcircuitry,” Cell, Oct. 8, 2015, 163:456-492. [cited by applicant]
McCoss, Agency of Life, Entropic Gravity and Phenomena Attributed to “Dark Matter,” Journal of Quantum Information Science, Jun. 15, 2017, 7:67-75. [cited by applicant]
McCoss, “Lithium Quantum Consciousness,” Journal of Quantum Information Science, Nov. 8, 2017, 7:125-139. [cited by applicant]
Meyer et al., “Cell type-specific thalamic innervation in a col. of rat vibrissal cortex,” Cereb. Cortex, Jun. 9, 2010, 20: 2287-2303. [cited by applicant]
Miller et al., “Visual stimuli recruit intrinsically generated cortical ensembles,” Proc. Natl. Acad. Sci. U.S.A., Sep. 8, 2014, pp. E4053-E4061. [cited by applicant]
Miura et al., “Sparse Parallel Algorithms for Recognizing Touch Topology on Curved Interactive Screens,” IEEE Access, Jul. 31, 2017, 5:14889-14897. [cited by applicant]
Munkres, “Elements of Algebraic Topology,” Massachusetts Institute of Technology, 1984, Addison-Wesley Publishing Company, 233 pages. [cited by applicant]
Opris et al., “What Is the Evidence for Inter-laminar Integration in a Prefrontal Cortical Minicolumn?,” Frontiers in Neuroanatomy, Dec. 14, 2017, 11: 1-11. [cited by applicant]
Pajevic et al., “The organization of strong links in complex networks,” Nat. Phys., Mar. 11, 2012, 8:429-436. [cited by applicant]
Palm et al., “On the significance of correlations among neuronal spike trains,” Biol. Cybern., Jun. 1, 1988, 59:1-11. [cited by applicant]
Patel et al., “Generative Design of Electromagnetic Structures Through Bayesian Learningm,” IEEE Transactions on Magnetics, Oct. 20, 2017, 54:1-4. [cited by applicant]
Pedregosa et al., “Scikit-learn: machine learning in Python,” J. Mach. Learn. Res., Oct. 2010, 12:2825-2830. [cited by applicant]
Perin et al., “A synaptic organizing principle for cortical neuronal groups,” Proc. Natl. Acad. Sci. U.S.A., Mar. 29, 2011, 108:5419-5424. [cited by applicant]
Peters et al., “The projection of the lateral geniculate nucleus to area 17 of the rat cerebral cortex. I General description.,” J. Neurocytol., Feb. 1976, 5:63-84. [cited by applicant]
Petlevski, “Modeling the Model: the World Beyond the Immediate Sensorium, ” Proceedings of the 20th International Multiconference Information Society, Oct. 18, 2017, pp. 44-47. [cited by applicant]
Petri et al., “Homological scaffolds of brain functional networks,” J. R. Soc. Interface, Dec. 6, 2014, 1:1-11. [cited by applicant]
Planas et al., “Accelerating Data Analysis in Simulation Neuroscience with Big Data Technologies,” International Conference on Computational Science, Jun. 1, 2018, pp. 363-377. [cited by applicant]
Ramaswamy et al., “The neocortical microcircuit collaboration portal: a resource for rat somatosensory cortex,” Front. Neural Circuits, Oct. 8, 2015, 9:1-14. [cited by applicant]
Reimann et al. “An algorithm to predict the connectome of neural microcircuits,” Front. Comput. Neurosci., Oct. 8, 2015, 9:1-18. [cited by applicant]
Renart et al., “The asynchronous state in cortical circuits,” Science 327, Jan. 29, 2010, 587-590. [cited by applicant]
Rosenbaum et al., “The spatial structure of correlated neuronal variability,” Nat. Neurosci., Oct. 21, 2016, 20:107-114. [cited by applicant]
SciPy.org [online], “ SciPy: Open Source Scientific Tools for Python,” available on or before Mar. 9, 2001, via Internet Achieve: Wayback Machine URL <https://web.archive.org/web/20010309040805/http://www.scipy.org/>, r… [cited by applicant]
See et al., “Coordinated neuronal ensembles in primary auditory cortical columns,” Elife Sciences, Jun. 5, 2018, pp. 1-33. [cited by applicant]
Shepherd et al., “Geometric and functional organization of cortical circuits,” Nat. Neurosci., May 8, 2005, 8:782-790. [cited by applicant]
Song et al. “Highly nonrandom features Of synaptic connectivity in local cortical circuits,” PLoS Biol., Mar. 1, 2005, 3:0507-0519. [cited by applicant]
Stepanyants et al., “Neurogeometry and potential synaptic connectivity,” Trends in Neurosci., Jun. 2, 2005, 28:387-394. [cited by applicant]
Suarez, “The interaction between task goals and the representation of choice options in decision-making,” Thesis for the degree of Doctor of Philosophy, University College of London, Sep. 2017, pp. 1-176. [cited by applicant]
Tozzi et al., “Brain Projective Reality: Novel Clothes for the Emperor, Reply to comments of “Topodynamics of metastable brains,” by Tozzi et al.” Physics of Life Reviews, Jun. 28, 2017, pp. 1-11. [cited by applicant]
Tyukin et al., “High-Dimensional Brain: A Tool for Encoding and Rapid Learning of Memories by Single Neurons,” Bull Math Biol., Mar. 19, 2018, 11:4856-4888. [cited by applicant]
Varshney et al., “Structural properties of the caenorhabditis elegans neuronal network,” PLoS Comput. Biol., Feb. 3, 2011, 7:1-22. [cited by applicant]
Wijaya et al., “Finding an appropriate equation to measure similarity between binary vectors: case studies on Indonesian and Japanese herbal medicines,” BMC bioinformatics, Dec. 2016,17:1-19. [cited by applicant]
Willshaw et al., “Nonholographic associative memory,” Nature 222, Jun. 7, 1969, pp. 960-963. [cited by applicant]
Guerreiro et al., “A Neural Key Generator for a Public Block Cipher,” IEEE Ninth Brazilian Symposium on Neural Networks (SBRN '06), Oct. 23-27, 2006, Ribeirao Preto, BR, 143-147. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/056588, dated May 26, 2020, 12 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/056686, dated May 26, 2020, 13 pages. [cited by applicant]
Bahraini et al., “Topological pattern selection in recurrent networks,” Neural Networks, Feb. 9, 2012, 31:22-32. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/085007, dated Mar. 24, 2021, 15 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/085016, dated Mar. 24, 2021, 18 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/085169, dated Mar. 18, 2021, 15 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/085200, dated Apr. 4, 2021, 15 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2020/085434, dated Mar. 24, 2021, 16 pages. [cited by applicant]
Salnikov et al., “Simplicial complexes and complex systems,” arxiv.org, Cornell University Library, Jul. 20, 2018, 8 pages. [cited by applicant]
Yang et al., “Road Detection and Centerline Extraction via Deep Recurrent Convolutional Neutral Network U-Net,” IEEE Transactions on Geoscience and Remote Sensing, Sep. 2019, 57(9):7209-7220. [cited by applicant]
Cai et al., “Path-level network transformation for efficient architecture search,” InInternational Conference on Machine Learning, Jul. 3, 2018 PMLR, 10 pages. [cited by applicant]
Ludermir et al., “An optimization methodology for neural network weights and architectures,” IEEE Transactions on Neural Networks, Nov. 13, 2006, 17(6):1452-9. [cited by applicant]
Rawal et al., “From nodes to networks: Evolving recurrent neural networks,” arXiv preprint arXiv:1803.04439, Mar. 12, 2018, 8 pages. [cited by applicant]
Lena et al., “Deep spatio-temporal architectures and learning for protein structure prediction,” Advances in neural information processing systems, 25, 2012, 9 pages. [cited by applicant]
Park et al., “CNN (Convolutional Neural Network) based in-loop filter in HEVC,” In Proceedings of the Korean Society of Broadcast Engineers Conference 2016, The Korean Institute of Broadcast and Media Engineers, 2016, p… [cited by applicant]
Wang et al., “Topological recurrent neural network for diffusion prediction,” In2017 IEEE International Conference on Data Mining (ICDM), Nov. 18, 2017, pp. 475-484. [cited by applicant]
Masulli et al., “Dynamics of evolving feed-forward neural networks and their topological invariants,” Network and Parallel Computing, Aug. 13, 2016, pp. 99-106. [cited by applicant]
Bauer et al., “Real-time ultra-low power ECG anomaly detection using an event-driven neuromorphic processor,” IEEE transactions on biomedical circuits and systems, Nov. 11, 2019, 13(6):1575-82. [cited by applicant]
Goodman et al., “Brian: a simulator for spiking neural networks in python,” Frontiers in neuroinformatics, 2008:5, 10 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/085007, dated Jun. 23, 2022, 8 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/085016, dated Jun. 23, 2022, 11 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/085169, dated Jun. 23, 2022, 8 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/085200, dated Jun. 23, 2022, 9 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/085434, dated Jun. 23, 2022, 9 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/085716, dated Jun. 23, 2022, 11 pages. [cited by applicant]
International Search Report and Written Opinion in International Appln. No. PCT/EP2020/085716 , dated Mar. 25, 2021, 18 pages. [cited by applicant]
Minkovich et al. “Programming time-multiplexed reconfigurable hardware using a scalable neuromorphic compiler,” IEEE transactions on neural networks and learning systems, Apr. 11, 2012, 23(6):889-901. [cited by applicant]
U.S. Appl. No. 17/783,961, filed Jun. 9, 2022, Markram. [cited by applicant]
Andersen et al., “Overlapping clusters for distributed computation,” In Proceedings of the Fifth ACM International Conference on Web Search and Data Mining, Feb. 8, 2012, 9 pages. [cited by applicant]
Baskararaja et al., “Subgraph matching using graph neural network,” Journal of Intelligent Learning Systems and Applications, Nov. 28, 2012, 4(04):274-278. [cited by applicant]
Bauer et al., “Clear and Compress: Computing Persistent Homology in Chunks,” Topological Methods in Data Analysis and Visualization III., 2014, pp. 103-117. [cited by applicant]
Cormen et al., “Introduction to Algorithms,” Copyright 2001 by The Massachusetts Institute of Technology, 984 pages. [cited by applicant]
Erdos and Renyi, “On random graphs, I,” Math. Debrecen., 1959, 6:290-297. [cited by applicant]
Gros, “Cognitive computation with autonomously active neural networks: an emerging field,” Cognitive Computation, Mar. 2009, 1(1):77-90. [cited by applicant]
Gros, “Neural networks with transient state dynamics,” New Journal of Physics, Apr. 30, 2007, 9(4):109, 21 pages. [cited by applicant]
Gros, “Self-sustained thought processes in a dense associative network,” In Annual Conference on Artificial Intelligence, Sep. 11, 2005, Springer, Berlin, Heidelberg, 14 pages. [cited by applicant]
Hatcher, “Algebraic Topology,” Cambridge University Press, Feb. 2002, 556 pages. [cited by applicant]
Kahle, “Sharp vanishing thresholds for cohomology of random flag complexes,” Ann. of Math., May 2014, 179(3):1085-1107. [cited by applicant]
Lin et al., “Organizing principles of real-time memory encoding: neural clique assemblies and universal neural codes,” TRENDS in Neurosciences, Jan. 2006, 29(1):48-57. [cited by applicant]
Maria, “Algorithms and data structures in computational topology” (Doctoral dissertation, Université Nice Sophia Antipolis), Oct. 28, 2014, 205 pages. [cited by applicant]
mathworld.wolfram.com [online], “Adjacency Matrix,” 2016, retrieved via Internet Archive on Apr. 8, 2022, retrieved from <https://web.archive.org/web/20160311204902/https://mathworld.wolfram.com/AdjacencyMatrix.htm1>, 2… [cited by applicant]
Milo et al., “Network Motifs: Simple Building Blocks of Complex Networks,” Science, Oct. 25, 2002, 298(5594):824-827. [cited by applicant]
Peters et al., “The projection of the lateral geniculate nucleus to area 17 of the rat cerebral cortex. V. Degenerating axon terminals synapsing with Golgi impregnated neurons,” J Neurocytol., 1979, 8:331-357. [cited by applicant]
Srivastava et al., “Dropout: a simple way to prevent neural networks from overfitting,” The journal of machine learning research, Jan. 2014, 15(1):1929-58. [cited by applicant]
TW Office Action in Taiwanese Appln. No. 10943863, dated Mar. 1, 2022, 13 pages (with machine translation). [cited by applicant]
U.S. Appl. No. 16/004,635, filed Jun. 11, 2018, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/004,837, filed Jun. 11, 2018, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/004,757, filed Jun. 11, 2018, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/004,671, filed Jun. 11, 2018, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/356,391, filed Mar. 18, 2019, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/356,478, filed Mar. 18, 2019, Kathryn Hess. [cited by applicant]
U.S. Appl. No. 16/710,266, filed Dec. 11, 2019, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/710,058, filed Dec. 11, 2019, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/710,205, filed Dec. 11, 2019, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/710,176, filed Dec. 11, 2019, Henry Markram. [cited by applicant]
U.S. Appl. No. 16/710,080, filed Dec. 11, 2019, Henry Markram. [cited by applicant]
U.S. Appl. No. 15/864,146, filed Jan. 8, 2018, Michael Wolfgang Reimann. [cited by applicant]
Baker et al., “Designing neural network architectures using reinforcement learning,” arXiv preprint, arXiv:1611.02167, Nov. 7, 2016, 18 pages. [cited by applicant]
Chambers et al., “Higher-order synaptic interactions coordinate dynamics in recurrent networks,” PLoS computational biology, Aug. 19, 2016, 12(8):e1005078, 23 pages. [cited by applicant]
EP Extended European Search Report in EP Appln. No. 17174314.9, dated Dec. 14, 2017, 11 pages. [cited by applicant]
Garcia et al., “Unsupervised classification of neural spikes with a hybrid multilayer artificial neural network,” Journal of Neuroscience Methods, 1998, 82:59-73. [cited by applicant]
Giusti et al., “Two's company, three (or more) is a simplex,” Journal of computational neuroscience, Aug. 2016, 41(1):1-14. [cited by applicant]
Graves, “Adaptive computation time for recurrent neural networks,” arXiv preprint arXiv: 1603.08983, Mar. 29, 2016, 19 pages. [cited by applicant]
Gros et al., “Semantic learning in autonomously active recurrent neural networks,” Logic Journal of IGPL, Oct. 1, 2010, 18(5):686-704. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/056588, dated Sep. 30, 2021, 8 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/EP2020/056686, dated Sep. 30, 2021, 10 pages. [cited by applicant]
Sizemore et al., “Cliques and cavities in the human connectome,” Journal of computational neuroscience, Feb. 2018, 44(1):115-45. [cited by applicant]
Achard et al., “A Resilient, Low-Frequency, Small-World Human Brain Functional Network with Highly Connected Association Cortical Hubs,” Journal of Neuroscience, Jan. 4, 2006, 26(1):63-72. [cited by applicant]
Arai et al., “The Effects of Theta Precession on Spatial Learning and Simplicial Complex Dynamics in a Topological Model of the Hippocampal Spatial Map,” PLOS Computational Biology, Jun. 19, 2014, 10(6):r1003651. [cited by applicant]
Astrivis [online], “Demo Scan Church Dec. 2016,” Dec. 2, 2016, retrieved on Nov. 27, 2022, retrieved from URL <https://www.youtube.com/watch?v=xCgQ4aaB1Go>, 2 pages [Video Submission]. [cited by applicant]
Bassett et al., “Dynamic reconfiguration of human brain networks during learning,” PNAS, Apr. 18, 2011, 108(18):7641-7646. [cited by applicant]
Brown et al., “Structure of the Afferent Terminals in Terminal Ganglion of a Cricket and Persistent Homology, ” PLOS One, May 23, 2012, 7(5):e37278. [cited by applicant]
Chen et al., “Neural Representation of Spatial Topology in the Rodent Hippocampus,” Neural Computation, Jan. 2014, 26(1):1-39. [cited by applicant]
Choi et al., “Abnormal metabolic connectivity in the pilocarpine-induced epilepsy rat model: A multiscale network analysis based on persistent homology,” NeuroImage, Oct. 1, 2014, 99:226-236. [cited by applicant]
Chung et al., “Persistence Diagrams of Cortical Surface Data,” Information Processing in Medical Imaging, 2009, pp. 386-397. [cited by applicant]
Crossley et al., “Cognitive relevance of the community structure of the human brain functional coactivation network,” PNAS, Jun. 24, 2013, 110(28):11583-11588. [cited by applicant]
Dongjiang et al., “DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features,” ArXiv, Aug. 12, 2020, 8 pages. [cited by applicant]
Drakesmith et al., “Overcoming the effects of false positives and threshold bias in graph theoretical analyses of neuroimaging data,” NeuroImage, Sep. 2015, 118:313-333. [cited by applicant]
Ellis et al., “Describing High-Order Statistical Dependence Using “Concurrence Topology,” With Application to Functional MRI Brain Data,” Homology, Homotopy and Applications, 2014, 16(1):245-264. [cited by applicant]
Garrison et al., “The (in)stability of functional brain network measures across thresholds,” NeuroImage, Sep. 2015, 118:651-661. [cited by applicant]
Ginestet et al., “Brain Network Analysis: Separating Cost from Topology Using Cost-Integration,” PLOS One, Jul. 28, 2018, 2011, 6(7):e21570. [cited by applicant]
International Search Report and Written Opinion in International Appln. No. PCT/EP2022/073852, mailed on Dec. 9, 2022, 18 pages. [cited by applicant]
Khalid et al., “Tracing the evolution of multi-scale functional networks in a mouse model of depression using persistent brain network homology,” NeuroImage, Nov. 1, 2014, 101:351-363. [cited by applicant]
Kim et al., Morphological brain network assessed using graph theory and network filtration in deaf adults, Hearing Research, Sep. 2014, 315:88-98. [cited by applicant]
Langer et al., “The Problem of Thresholding in Small-World Network Analysis, ” PLOS One, Jan. 3, 2013, 8(1):e53199. [cited by applicant]
Lee et al., “Discriminative persistent homology of brain networks,” 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Mar. 30, 2011, pp. 841-844. [cited by applicant]
Lucky Robot [online], “ORB SLAM3: Ar demo,” Feb. 23, 2021, retrieved on Nov. 27, 2022, retrieved from URL <https://www.youtube.com/watch?v=c1ExX_IA5tM>, 2 pages [Video Submission]. [cited by applicant]
Medaglia et al., “Cognitive Network Neuroscience,” Journal of Cognitive Neuroscience, Aug. 1, 2015, 27(8):1471-1491. [cited by applicant]
Mur-Artal et al., “ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras,” IEEE Transactions on Robotics, Oct. 5, 2015, 31(5):1147-1163. [cited by applicant]
Pirino et al., “A topological study of repetitive co-activation networks in in vitro cortical assemblies,” Physical Biology, Jan. 5, 2015, 12(1):016007. [cited by applicant]
Singh et al., “Topological analysis of population activity in visual cortex,” Journal of Vision, Jun. 2008, 8(8):11, 18 pages. [cited by applicant]
Stolz, “Computational Topology in Neuroscience,” Dissertation for the Degree of Master of Science in Mathematical Modelling & Scientific Computing at the University of Oxford, Sep. 2014, 77 pages. [cited by applicant]
Alaniz, “Machiavellian Playbook for Artificial General Intelligence (AGI), Early Doctrine for AGI power,” Research Gate, Aug. 2018, pp. 1-42. [cited by applicant]
Alaniz, “Remaking Einstein with a Dynamical Graph Rich Person Object Avatar Extraction Markup Language (intelligence as topological algebraic invariants, graph entropies, and dynamics),” Mar. 16, 2019, 14 pages. [cited by applicant]
Allswede et al., “Prenatal inflammation and risk for schizophrenia: A role for immune proteins in neurodevelopment,” Development and Psychopathology, Aug. 2, 2018, 30: 1157-1178. [cited by applicant]
Antonopoulos et al., “Evaluating performance of neural codes in neural communication networks,” Neural Networks, Sep. 24, 2018, pp. 1-17. [cited by applicant]
Baptiste-Bardin et al., “Topological exploration of artificial neuronal network dynamics,” Network Neuroscience, Jan. 24, 2019, pp. 1-28. [cited by applicant]
Basset et al., “Network models in neuroscience,” arXiv, Jul. 21, 2018, pp. 1-12. [cited by applicant]
Basset et al., “On the nature and use of models in network neuroscience,” Nature Reviews, Jul. 12, 2018, 19:566-578. [cited by applicant]
Baudot et al., “Topological Information Data Analysis,” Entropy, Sep. 2019, 21:1-38. [cited by applicant]
Betzel, “Stability of spontaneous, correlated activity in mouse auditory cortex,” PLOS: Computational Biology, Dec. 9, 2019, 1-25. [cited by applicant]
Bianconi et al., “Topological percolation on hyperbolic simplicial complexes,” Phys. Rev. E, Nov. 21, 2018, 5:1-18. [cited by applicant]