20250173573. Recurrent Neural Network Training (Arm Limited)

RECURRENT NEURAL NETWORK TRAINING WITH HISTORY

Abstract: a persistent history buffer may be maintained in training a recurrent neural network such that information from at least one prior group of sequential training parameters within a training sequence is maintained for a subsequent group of training parameters. the persistent history buffer may be provided as an input to the recurrent neural network, and may store a history of a state of the recurrent neural network such as an input, an output and/or the state of a hidden layer. the persistent history buffer may be reset at the end of a sequence of input training parameters, which in a further example may span training input windows and/or batches.

Inventor(s): Ridhwanul Haque, Liam James O'Neil, Yanxiang Wang, Joshua James Sowerby, Maxim Novikov

CPC Classification: G06N3/084 (Backpropagation, e.g. using gradient descent)

Search for rejections for patent application number 20250173573