IP Library › Granted Patent US 12,379,977
Granted Patent B2
US 12,379,977 · App. 18/360,482 · Granted Aug 5, 2025

Systems and methods for synthetic data generation for time-series data using data segments

Inventors: Austin Walters (Savoy, IL); Mark Watson (Urbana, IL); Anh Truong (Champaign, IL); Jeremy Goodsitt (Champaign, IL); Reza Farivar (Champaign, IL); Kate Key (Effingham, IL); Vincent Pham (Champaign, IL); Galen Rafferty (Mahomet, IL)
Assignee: Capital One Services, LLC
G06F9/541G06F8/71G06F9/54G06F9/547G06F11/3608G06F11/3628G06F11/3636G06F16/2237G06F16/2264G06F16/2423G06F16/24568G06F16/248G06F16/254G06F16/258G06F16/283G06F16/285G06F16/288G06F16/335G06F16/90332G06F16/90335G06F16/9038G06F16/906G06F16/93G06F17/15G06F17/16G06F17/18G06F18/2115G06F18/213G06F18/214G06F18/2148G06F18/217G06F18/2193G06F18/22G06F18/23G06F18/24G06F18/2411G06F18/2415G06F18/285G06F18/40G06F21/552G06F21/60G06F21/6245G06F21/6254G06F30/20G06F40/117G06F40/166G06F40/20G06N3/04G06N3/044G06N3/045G06N3/06G06N3/08G06N3/088G06N3/094G06N5/00G06N5/02G06N5/04G06N7/00G06N7/01G06N20/00G06Q10/04G06T7/194G06T7/246G06T7/248G06T7/254G06T11/001G06V10/768G06V10/993G06V30/194G06V30/1985H04L63/1416H04L63/1491H04L67/306H04L67/34H04N21/23412H04N21/8153G06T2207/10016G06T2207/20081G06T2207/20084
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 12,379,977
App. No.
18/360,482
Granted
Aug 5, 2025
Kind
B2
Abstract

Systems and methods for generating synthetic data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a dataset including time-series data. The operations may include generating a plurality of data segments based on the dataset, determining respective segment parameters of the data segments, and determining respective distribution measures of the data segments. The operations may include training a parameter model to generate synthetic segment parameters. Training the parameter model may be based on the segment parameters. The operations may include training a distribution model to generate synthetic data segments. Training the distribution model may be based on the distribution measures and the segment parameters. The operations may include generating a synthetic dataset using the parameter model and the distribution model and storing the synthetic dataset.

Claims (34)

1. A system for facilitating realistic synthetic time-series data generation via time-scale-based distribution measures, comprising:

one or more processors and one or more memory units storing instructions that, when executed by the one or more processors, perform operations comprising:

storing, in a network database, reference time-series data segments comprising reference subsets of reference data segments that respectively correspond to different time scales;

during training of a machine learning model, executing, via a network, the machine learning model to generate synthetic time-series data segments comprising synthetic subsets of synthetic data segments that respectively correspond to the different time scales;

with respect to a first time scale of the different time scales, loading, from a network database, a first reference subset of the reference time-series data segments that corresponds to the first time scale in connection with autocorrelation of a first synthetic subset of the synthetic time-series data segments that corresponds to the first time scale; and

based on a comparison of an autocorrelation of (i) a reference distribution measure associated with the first reference subset of the reference time-series data segments that corresponds to the first time scale and (ii) a synthetic distribution measure associated with the first synthetic subset of the synthetic time-series data segments that corresponds the first time scale, performing (i) updating of the machine learning model in connection with the training of the machine learning model or (ii) termination of the training of the machine learning model.

2. A method for generating synthetic data, the method comprising:

storing, in one or more databases, reference time-series data segments;

during training of a machine learning model, executing the machine learning model to generate synthetic time-series data segments;

with respect to a first time scale, obtaining a first reference subset of the reference time-series data segments that corresponds to the first time scale in connection with autocorrelation of a first synthetic subset of the synthetic time-series data segments that corresponds to the first time scale; and

based on a comparison of an autocorrelation of (i) a reference distribution measure associated with the first reference subset of the reference time-series data segments and (ii) a synthetic distribution measure associated with the first synthetic subset of the synthetic time-series data segments, performing (i) updating of the machine learning model in connection with the training of the machine learning model or (ii) termination of the training of the machine learning model.

3. The method of claim 2 , wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a given comparison with respect to a regression of a time-based function applied to the first reference subset of the reference time-series data segments and a regression of a time-based function applied to the first synthetic subset of the synthetic time-series data segments.

4. The method of claim 2 , wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a performance metric derived from the comparison.

5. The method of claim 2 , wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a similarity metric derived from the comparison.

6. The method of claim 2 , further comprising generating a synthetic dataset by combining sequences of the synthetic time-series data segments.

7. The method of claim 2 , wherein the reference distribution measure comprises at least one of a normalized distribution, a gaussian distribution, a Bernoulli distribution, a binomial distribution, a normal distribution, a Poisson distribution, or an exponential distribution.

8. The method of claim 2 , wherein generating the synthetic time-series data segments comprises, during the training of the machine learning model, executing the machine learning model to generate (i) first synthetic time-series data segments that corresponds to the first time scale and (ii) second synthetic time-series data segments that correspond to a second time scale different from the first time scale.

9. The method of claim 2 ,

wherein generating the synthetic time-series data segments comprises, during the training of the machine learning model, executing the machine learning model to generate synthetic three-dimensional time-series spatial data that corresponds to the first time scale, and

wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a given comparison of the reference distribution measure and a given synthetic distribution measure associated with the synthetic three-dimensional time-series spatial data that corresponds to the first time scale.

10. One or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors, causes operations comprising:

storing, in one or more databases, reference time-series data segments;

during training of a machine learning model, executing the machine learning model to generate synthetic time-series data segments;

with respect to a first time scale, obtaining a first reference subset of the reference time-series data segments that corresponds to the first time scale in connection with autocorrelation of a first synthetic subset of the synthetic time-series data segments that corresponds to the first time scale; and

based on a comparison of an autocorrelation of (i) a reference distribution measure associated with the first reference subset of the reference time-series data segments and (ii) a synthetic distribution measure associated with the first synthetic subset of the synthetic time-series data segments, performing (i) updating of the machine learning model in connection with the training of the machine learning model or (ii) termination of the training of the machine learning model.

11. The one or more non-transitory computer-readable media of claim 10 , wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a given comparison with respect to a regression of a time-based function applied to the first reference subset of the reference time-series data segments and a regression of a time-based function applied to the first synthetic subset of the synthetic time-series data segments.

12. The one or more non-transitory computer-readable media of claim 10 , wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a performance metric derived from the comparison.

13. The one or more non-transitory computer-readable media of claim 10 , wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a similarity metric derived from the comparison.

14. The one or more non-transitory computer-readable media of claim 10 , further comprising generating a synthetic dataset by combining sequences of the synthetic time-series data segments.

15. The one or more non-transitory computer-readable media of claim 10 , wherein the reference distribution measure comprises at least one of a normalized distribution, a gaussian distribution, a Bernoulli distribution, a binomial distribution, a normal distribution, a Poisson distribution, or an exponential distribution.

16. The one or more non-transitory computer-readable media of claim 10 , wherein generating the synthetic time-series data segments comprises, during the training of the machine learning model, executing the machine learning model to generate (i) first synthetic time-series data segments that corresponds to the first time scale and (ii) second synthetic time-series data segments that correspond to a second time scale different from the first time scale.

17. The one or more non-transitory computer-readable media of claim 10 ,

wherein generating the synthetic time-series data segments comprises, during the training of the machine learning model, executing the machine learning model to generate synthetic three-dimensional time-series spatial data that corresponds to the first time scale, and

wherein performing the updating of the machine learning model or the termination of the training of the machine learning model comprises performing the updating of the machine learning model or the termination of the training of the machine learning model based on a given comparison of the reference distribution measure and a given synthetic distribution measure associated with the synthetic three-dimensional time-series spatial data that corresponds to the first time scale.

Continuity (4)
Continuation 17102526 · Nov 24, 2020
Continuation 16405989 · May 7, 2019
Provisional Application 62694968 · Jul 6, 2018
Related Publication 20230376362A1 · Nov 23, 2023
References Cited (175)
US 5911139A · Jain et al. · 1999 [cited by applicant]
US 5974549A · Golan · 1999 [cited by applicant]
US 6137912A · Kostrzewski et al. · 2000 [cited by applicant]
US 6269351B1 · Black · 2001 [cited by applicant]
US 6456990B1 · Hofmann et al. · 2002 [cited by applicant]
US 7788191B2 · Jebara · 2010 [cited by applicant]
US 7953682B2 · Smith et al. · 2011 [cited by applicant]
US 8375014B1 · Brocato et al. · 2013 [cited by applicant]
US 8375032B2 · Birdwell et al. · 2013 [cited by applicant]
US 8392418B2 · Birdwell et al. · 2013 [cited by applicant]
US 8484215B2 · Anderson · 2013 [cited by applicant]
US 8548951B2 · Solmer et al. · 2013 [cited by applicant]
US 8706659B1 · Mann et al. · 2014 [cited by applicant]
US 8782744B1 · Fuller et al. · 2014 [cited by applicant]
US 8990236B2 · Mizrahy et al. · 2015 [cited by applicant]
US 9171146B2 · Vipat et al. · 2015 [cited by applicant]
US 9274935B1 · Lachwani et al. · 2016 [cited by applicant]
US 9462013B1 · Boss et al. · 2016 [cited by applicant]
US 9497202B1 · Calo et al. · 2016 [cited by applicant]
US 9608809B1 · Ghetti et al. · 2017 [cited by applicant]
US 9678999B1 · Gibas et al. · 2017 [cited by applicant]
US 9716842B1 · Worley et al. · 2017 [cited by applicant]
US 9754190B1 · Guttmann · 2017 [cited by applicant]
US 9886247B2 · Laredo et al. · 2018 [cited by applicant]
US 9912698B1 · Thioux et al. · 2018 [cited by applicant]
US 9954893B1 · Zhao et al. · 2018 [cited by applicant]
US 10122969B1 · Lim et al. · 2018 [cited by applicant]
US 10212428B2 · Trepte · 2019 [cited by applicant]
US 10282907B2 · Miller et al. · 2019 [cited by applicant]
US 10380236B1 · Ganu et al. · 2019 [cited by applicant]
US 10453220B1 · Mihal et al. · 2019 [cited by applicant]
US 10733482B1 · Lee et al. · 2020 [cited by applicant]
US 10860629B1 · Gangadharaiah et al. · 2020 [cited by applicant]
US 20020103793A1 · Koller et al. · 2002 [cited by applicant]
US 20030003861A1 · Kagemoto et al. · 2003 [cited by applicant]
US 20030074368A1 · Schuetze et al. · 2003 [cited by applicant]
US 20060031622A1 · Jardine · 2006 [cited by applicant]
US 20060123009A1 · Bruno · 2006 [cited by examiner]
US 20070169017A1 · Coward · 2007 [cited by applicant]
US 20070271287A1 · Acharya et al. · 2007 [cited by applicant]
US 20080168339A1 · Hudson et al. · 2008 [cited by applicant]
US 20080270363A1 · Hunt et al. · 2008 [cited by applicant]
US 20080288424A1 · Iyengar · 2008 [cited by examiner]
US 20080288889A1 · Hunt et al. · 2008 [cited by applicant]
US 20090018996A1 · Hunt et al. · 2009 [cited by applicant]
US 20090055331A1 · Stewart · 2009 [cited by applicant]
US 20090055477A1 · Flesher et al. · 2009 [cited by applicant]
US 20090110070A1 · Takahashi et al. · 2009 [cited by applicant]
US 20090254971A1 · Herz et al. · 2009 [cited by applicant]
US 20100251340A1 · Martin et al. · 2010 [cited by applicant]
US 20100254627A1 · Tehrani et al. · 2010 [cited by applicant]
US 20100332210A1 · Birdwell et al. · 2010 [cited by applicant]
US 20100332474A1 · Birdwell et al. · 2010 [cited by applicant]
US 20110106743A1 · Duchon · 2011 [cited by applicant]
US 20120174224A1 · Thomas et al. · 2012 [cited by applicant]
US 20120284213A1 · Lin et al. · 2012 [cited by applicant]
US 20120303633A1 · He · 2012 [cited by examiner]
US 20130117830A1 · Erickson et al. · 2013 [cited by applicant]
US 20130124526A1 · Birdwell · 2013 [cited by applicant]
US 20130159309A1 · Birdwell et al. · 2013 [cited by applicant]
US 20130159310A1 · Birdwell et al. · 2013 [cited by applicant]
US 20130167192A1 · Hickman et al. · 2013 [cited by applicant]
US 20140053061A1 · Chasen et al. · 2014 [cited by applicant]
US 20140195466A1 · Phillipps et al. · 2014 [cited by applicant]
US 20140201126A1 · Zadeh et al. · 2014 [cited by applicant]
US 20140278339A1 · Aliferis et al. · 2014 [cited by applicant]
US 20140317021A1 · Weber et al. · 2014 [cited by applicant]
US 20140324760A1 · Marwah et al. · 2014 [cited by applicant]
US 20140325662A1 · Foster et al. · 2014 [cited by applicant]
US 20140365549A1 · Jenkins · 2014 [cited by applicant]
US 20150032761A1 · Pasternack · 2015 [cited by applicant]
US 20150058388A1 · Smigelski · 2015 [cited by applicant]
US 20150066793A1 · Brown · 2015 [cited by applicant]
US 20150100537A1 · Grieves et al. · 2015 [cited by applicant]
US 20150134413A1 · Deshpande et al. · 2015 [cited by applicant]
US 20150220734A1 · Nalluri et al. · 2015 [cited by applicant]
US 20150241873A1 · Goldenberg et al. · 2015 [cited by applicant]
US 20150309987A1 · Epstein et al. · 2015 [cited by applicant]
US 20160019271A1 · Ma et al. · 2016 [cited by applicant]
US 20160037170A1 · Zhang et al. · 2016 [cited by applicant]
US 20160057107A1 · Call et al. · 2016 [cited by applicant]
US 20160092476A1 · Stojanovic et al. · 2016 [cited by applicant]
US 20160092557A1 · Stojanovic et al. · 2016 [cited by applicant]
US 20160110657A1 · Gibiansky et al. · 2016 [cited by applicant]
US 20160119377A1 · Goldberg et al. · 2016 [cited by applicant]
US 20160132787A1 · Drevo et al. · 2016 [cited by applicant]
US 20160162688A1 · Call et al. · 2016 [cited by applicant]
US 20160197803A1 · Talbot et al. · 2016 [cited by applicant]
US 20160308900A1 · Sadika et al. · 2016 [cited by applicant]
US 20160371601A1 · Grove et al. · 2016 [cited by applicant]
US 20170011105A1 · Shet et al. · 2017 [cited by applicant]
US 20170083990A1 · Hou et al. · 2017 [cited by applicant]
US 20170147930A1 · Bellala et al. · 2017 [cited by applicant]
US 20170220336A1 · Chen et al. · 2017 [cited by applicant]
US 20170236183A1 · Klein et al. · 2017 [cited by applicant]
US 20170249432A1 · Grantcharov · 2017 [cited by applicant]
US 20170249564A1 · Garvey et al. · 2017 [cited by applicant]
US 20170323327A1 · Pachisia et al. · 2017 [cited by applicant]
US 20170331858A1 · Clark, III et al. · 2017 [cited by applicant]
US 20170359570A1 · Holzer et al. · 2017 [cited by applicant]
US 20180018590A1 · Szeto et al. · 2018 [cited by applicant]
US 20180108149A1 · Levinshtein · 2018 [cited by applicant]
US 20180115706A1 · Kang et al. · 2018 [cited by applicant]
US 20180121797A1 · Prabhu et al. · 2018 [cited by applicant]
US 20180150548A1 · Shah et al. · 2018 [cited by applicant]
US 20180165475A1 · Veeramachaneni et al. · 2018 [cited by applicant]
US 20180165728A1 · McDonald et al. · 2018 [cited by applicant]
US 20180173730A1 · Copenhaver et al. · 2018 [cited by applicant]
US 20180173958A1 · Hu et al. · 2018 [cited by applicant]
US 20180181802A1 · Chen et al. · 2018 [cited by applicant]
US 20180198602A1 · Duffy et al. · 2018 [cited by applicant]
US 20180199066A1 · Ross · 2018 [cited by applicant]
US 20180204111A1 · Zadeh et al. · 2018 [cited by applicant]
US 20180240041A1 · Koch et al. · 2018 [cited by applicant]
US 20180248827A1 · Scharber et al. · 2018 [cited by applicant]
US 20180253894A1 · Krishan et al. · 2018 [cited by applicant]
US 20180260474A1 · Surdeanu et al. · 2018 [cited by applicant]
US 20180260704A1 · Sun et al. · 2018 [cited by applicant]
US 20180268255A1 · Surazhsky et al. · 2018 [cited by applicant]
US 20180268286A1 · Dasgupta · 2018 [cited by applicant]
US 20180276332A1 · Fan et al. · 2018 [cited by applicant]
US 20180307945A1 · Haigh · 2018 [cited by examiner]
US 20180307978A1 · Ar et al. · 2018 [cited by applicant]
US 20180336463A1 · Bloom · 2018 [cited by applicant]
US 20180367484A1 · Rodriguez et al. · 2018 [cited by applicant]
US 20190005142A1 · Tseng · 2019 [cited by applicant]
US 20190005657A1 · Gao et al. · 2019 [cited by applicant]
US 20190026956A1 · Gausebeck et al. · 2019 [cited by applicant]
US 20190034833A1 · Ding et al. · 2019 [cited by applicant]
US 20190035047A1 · Lim et al. · 2019 [cited by applicant]
US 20190042290A1 · Bailey et al. · 2019 [cited by applicant]
US 20190051051A1 · Kaufman et al. · 2019 [cited by applicant]
US 20190056722A1 · Abbaszadeh · 2019 [cited by examiner]
US 20190057509A1 · Lv et al. · 2019 [cited by applicant]
US 20190139641A1 · Itu et al. · 2019 [cited by applicant]
US 20190147371A1 · Deo et al. · 2019 [cited by applicant]
US 20190188605A1 · Zavesky et al. · 2019 [cited by applicant]
US 20190196600A1 · Rothberg et al. · 2019 [cited by applicant]
US 20190220653A1 · Wang et al. · 2019 [cited by applicant]
US 20190228495A1 · Tremblay · 2019 [cited by examiner]
US 20190251397A1 · Tremblay et al. · 2019 [cited by applicant]
US 20190286938A1 · Backhus · 2019 [cited by examiner]
US 20190294923A1 · Riley et al. · 2019 [cited by applicant]
US 20190354836A1 · Shah et al. · 2019 [cited by applicant]
US 20190370431A1 · Sha · 2019 [cited by examiner]
US 20190370432A1 · Sha · 2019 [cited by examiner]
US 20200012896A1 · Yoo · 2020 [cited by examiner]
US 20200193288A1 · Li et al. · 2020 [cited by applicant]
US 20200272422A1 · Okada · 2020 [cited by examiner]
US 20200276680A1 · Green · 2020 [cited by examiner]
US 20210117420A1 · Pang et al. · 2021 [cited by applicant]
US 20210148213A1 · Madasu et al. · 2021 [cited by applicant]
US 20220405644A1 · Szeto · 2022 [cited by examiner]
WO WO02089054A1 · 2002 [cited by examiner]
Beaulieu-Jones et al., Privacy-preserving generative deep neural networks support 1 clinical data sharing, 7/52017, bioRxiv, total pages: 40, http://dx.doi.org/10.1101/159756 (Year: 2017). [cited by applicant]
Brkic et al., I Know That Person: Generative Full Body and Face De-Identification of People in Images, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1319-1328 (Year: 2017). [cited by applicant]
C. Willems, T. Holz and F. Freiling, “Toward Automated Dynamic Malware Analysis Using CWSandbox,” in IEEE Security & Privacy , vol. 5, No. 2, pp. 32-39, Mar.-Apr. 2007. (Year: 2007). [cited by applicant]
Dernoncourt, F., Lee, J. Y., Uzuner, 0., & Szolovits, P. (2017). De-identification of patient notes with recurrent neural networks. Journal of the American Medical Informatics Association, 24(3), 596-606. (Year: 2017). [cited by applicant]
Domadia, S. G., & Zaveri, T. (May 2011). Comparative analysis of unsupervised and supervised image classification techniques. In Proceeding of National Conference on Recent Trends in Engineering & Technology (pp. 1-5). … [cited by applicant]
Escovedo, Tatiana, et al. “DetectA: abrupt concept drift detection in non-stationary environments.” Applied Soft Computing 62 (2017 ): 119-133. (Year: 2017). [cited by applicant]
Gidaris, S., & Komodakis, N. (2017). Detect, replace, refine: Deep structured prediction for pixel wise labeling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5248-5257). (Year: … [cited by applicant]
Hasegawa et al. Interoperability for Mobile Agents by Incarnation Agents. AAMAS'Jul. 14-18, 03,2003, Melbourne, Australia. (Year: 2003). [cited by applicant]
Jiang, Z., Zhao, C., He, B., Guan, Y., & Jiang, J. (2017). De-identification of medical records using conditional random fields and long short-term memory networks. Journal of biomedical informatics, 75, S43-S53. (Year:… [cited by applicant]
Kim, Yoon. “Convolutional neural networks for sentence classification.” arXiv preprint arXiv: 1408. 5882 (2014). (Year: 2014). [cited by applicant]
Laszlo, M., & Mukherjee, S. (2013). Optimal univariate microaggregation with data suppression. Journal of Systems and Software, 86(3), 677-682. (Year: 2013). [cited by applicant]
Malekzadeh et al., Replacement Auto Encoder: A Privacy-Preserving Algorithm for Sensory Data Analysis, 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation, pp. 166-176 (Year: 201… [cited by applicant]
Marc Aurelio Ranzato, Arthur Szlam, Joan Bruna, Michael Mathieu, Ronan Collobert, and Sumit Chopra, “Video (Language) Modeling: A Baseline For Generative Models Of Natural Videos”, Article, May 4, 2016, 15 pages, Couran… [cited by applicant]
Matthias Feurer, Jost Tobias Springenberg, Aaron Klein, Manuel Blum, Katharina Eggensperger, and Frank Hutter, “Efficient and Robust Automated Machine Learning”, Advances in Neural Information Processing Systems 28 (Dec… [cited by applicant]
Park et al., Data Synthesis based on Generative Adversarial Networks, Aug. 2018, Proceedings of the VLDB Endowment, vol. 11, No. 10, pp. 1071-1083 (Year: 2018). [cited by applicant]
Qin Gao, Will Lewis, Chris Quirk, and Mei-Yuh Hwang. 2011. Incremental training and intentional over-fitting of word alignment. In Proceedings of MT Summit XIII. (Year: 2011). [cited by applicant]
Roberts, Mike. “Serverless Architectures”. https://martinfowler.com/articles/serverless.html. May 22, 2018. Accessed Jul. 22, 2019. (Year: 2018). [cited by applicant]
Vendrick, Carl, Hamed Pirsiavash, and Antonio Torralba. “Generating videos with scene dynamics.” Advances In Neural Information Processing Systems. 2016 (Year: 2016). [cited by applicant]
Wiktionary. “Spin Up”. https://en.wiktionary.org/w/index.php?title=spin_up&oldid=49727714. Jun. 15, 2018. Accessed Jul. 19, 2019. (Year: 2018). [cited by applicant]
Xue, Tianfan, et al. “Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks.” Advances in Neural Information Processing Systems. 2016 (Year: 2016). [cited by applicant]
Neha Patki, Roy Wedge, and Kalyan Veeramachanenl, “The Synthetic data vault”, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA) (Oct. 17, 2016) Cambridge, MA, 12 pp. [cited by applicant]