IP Library Patent Application 17476454
Patent Application
App. No. 17/476,454

METHODS AND DEVICES FOR NEURAL NETWORK QUANTIZATION USING TEMPORAL PROFILING

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 None
App. No.
17/476,454
Abstract

Methods and apparatuses are provided for temporal profiling for neural network quantization. The method includes: obtaining a neural network that comprises anode connected to different paths at different time periods; obtaining node outputs for the node at the different time periods; determining statistic properties of the node outputs at the different time periods; and determining activation ranges of the node outputs based on the statistic properties.

Claims (52)

1 . A method for neural network quantization, comprising:

obtaining a neural network that comprises a node connected to different paths at different time periods;

obtaining node outputs for the node at the different time periods;

determining statistic properties of the node outputs at the different time periods; and

determining activation ranges of the node outputs based on the statistic properties.

2 . The method of claim 1 , further comprising:

determining additional activation ranges for remaining nodes in the neural network; and

quantizing the neural network by quantizing each layer in the neural network and respectively quantizing each node output based on respective activation range.

3 . The method of claim 2 , wherein the neural network is a recurrent neural network for automatic speech recognition; and

wherein the method further comprises: implementing the recurrent neural network in an edge computing device after quantizing all neural network layers in the recurrent neural network.

4 . The method of claim 1 , wherein the neural network is one of following neural networks: a Long Short-Term Memory (LSTM), a LSTM with recurrent project layer (LSTMP), or a Gated Recurrent Unit (GRU).

5 . The method of claim 1 , wherein obtaining node outputs for the node at the different time periods further comprises:

multiplying input vectors of the node at the different time periods with weight matrices to obtain weighted matrices; and

concatenating the weighted matrices for further processing to obtain the node outputs.

6 . The method of claim 1 , wherein the statistic properties comprise one or a combination of following properties: a mean estimate, a histogram, a probability density function, a variance estimate, an entropy, a cross entropy, or a Kullback-Leiber Divergence.

7 . The method of claim 1 , wherein the neural network is a recurrent neural network for video recognition.

8 . An apparatus for implementing a neural network, comprising:

one or more processors; and

a memory configured to store instructions executable by the one or more processors;

wherein the one or more processors, upon execution of the instructions, are configured to:

obtain a neural network that comprises a node connected to different paths at different time periods;

obtain node outputs for the node at the different time periods;

determine statistic properties of the node outputs at the different time periods; and

determine activation ranges of the node outputs based on the statistic properties.

9 . The apparatus of claim 8 , wherein the one or more processors are further configured to:

determine additional activation ranges for remaining nodes in the neural network; and

quantize the neural network by quantizing each layer in the neural network and respectively quantizing each node output based on respective activation range.

10 . The apparatus of claim 9 , wherein the neural network is a recurrent neural network for automatic speech recognition; and

wherein the one or more processors are further configured to:

implement the recurrent neural network in an edge computing device after quantizing all neural network layers in the recurrent neural network.

11 . The apparatus of claim 8 , wherein the neural network is one of following neural networks: a Long Short-Term Memory (LSTM), a LSTM with recurrent project layer (LSTMP), or a Gated Recurrent Unit (GRU).

12 . The apparatus of claim 8 , wherein the one or more processors are further configured to:

multiply input vectors of the node at the different time periods with weight matrices to obtain weighted matrices; and

concatenate the weighted matrices for further processing to obtain the node outputs.

13 . The apparatus of claim 8 , wherein the statistic properties comprise one or a combination of following properties: a mean estimate, a histogram, a probability density function, a variance estimate, an entropy, a cross entropy or a Kullback-Leiber Divergence.

14 . The apparatus of claim 8 , wherein the neural network is a recurrent neural network for video recognition.

15 . A non-transitory computer readable storage medium, comprising instructions stored therein to implement a neural network, wherein, upon execution of the instructions by one or more processors, the instructions cause the one or more processors to perform acts comprising:

obtaining a neural network that comprises a node connected to different paths at different time periods;

obtaining node outputs for the node at the different time periods;

determining statistic properties of the node outputs at the different time periods; and

determining activation ranges of the node outputs based on the statistic properties.

16 . The non-transitory computer readable storage medium of claim 15 , wherein the instructions cause the one or more processors to further perform:

determining additional activation ranges for remaining nodes in the neural network; and

quantizing the neural network by quantizing each layer in the neural network and respectively quantizing each node output based on respective activation range.

17 . The non-transitory computer readable storage medium of claim 16 , wherein the neural network is a recurrent neural network for automatic speech recognition; and

wherein the instructions cause the one or more processors to further perform:

implementing the recurrent neural network in an edge computing device after quantizing all neural network layers in the recurrent neural network.

18 . The non-transitory computer readable storage medium of claim 15 , wherein the neural network is one of following neural networks: a Long Short-Term Memory (LSTM), a LSTM with recurrent project layer (LSTMP), or a Gated Recurrent Unit (GRU).

19 . The non-transitory computer readable storage medium of claim 15 , wherein obtaining node outputs for the node at the different time periods further comprises:

multiplying input vectors of the node at the different time periods with weight matrices to obtain weighted matrices; and

concatenating the weighted matrices for further processing to obtain the node outputs.

20 . The non-transitory computer readable storage medium of claim 15 , wherein the statistic properties comprise one or a combination of following properties: a mean estimate, a histogram, a probability density function, a variance estimate, an entropy, a cross entropy or a Kullback-Leiber Divergence.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 28, 2024
From: BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO. LTD.,
To: BEIJING TRANSTREAMS TECHNOLOGY CO. LTD.
Reel/Frame 066941/0319 →
CORRECTIVE ASSIGNMENT TO CORRECT THE APPLICATION 11830480 TO PATENT NUMBER PREVIOUSLY RECORDED AT REEL: 66622 FRAME: 672. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT . Recorded Mar 12, 2024
From: KWAI INC.
To: BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD.
Reel/Frame 066795/0775 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 1, 2024
From: KWAI INC.
To: BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD.
Reel/Frame 066622/0672 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 16, 2021
From: HSU, MING KAI; YANG, CHAO; MA, YUE; WANG, SIKAI; FENG, SITONG; CAO, WENHUI; LI, DANQING; ZHONG, HUI; LIU, LINGZHI
To: KWAI INC.
Reel/Frame 057499/0339 →