Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
TRAINING DEVICE, ESTIMATION DEVICE, METHOD FOR THESE, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2023/203690
Kind Code:
A1
Abstract:
Provided are a training device and the like that train a gated RNN so as to perform information processing utilizing the correlation between data at separate times in long series data without increasing the amount of memory and time required for calculation processing as much as prior art. The training device includes a gate calculation unit that obtains a gate zt,S at time t using the data xt,n,S at time t and the state vector ht-1,S at time t included in series data for training. The gate calculation unit uses an activation function γ that double-exponentially converges to 0 or 1 with respect to the input when obtaining the gate zt,S.

Inventors:
ONO KENTARO (JP)
Application Number:
PCT/JP2022/018311
Publication Date:
October 26, 2023
Filing Date:
April 20, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06N3/02
Other References:
GU, Albert et al. Improving the Gating Mechanism of Recurrent Neural Networks. Proceedings of the 37th International Conference on Machine Learning. 2020, vol. 119, pp. 3800-3809 [online], [retrieved on 05 July 2022], Retrieved from the Internet:
Attorney, Agent or Firm:
NAKAO, Naoki et al. (JP)
Download PDF: