US Patent:
20180260703, Sep 13, 2018
Inventors:
- Cambridge MA, US
Yichen Shen - Cambridge MA, US
Li Jing - Cambridge MA, US
Tena Dubcek - Zagreb, HR
Scott Skirlo - Belmont MA, US
John E. Peurifoy - Cambridge MA, US
Max Erik Tegmark - Winchester MA, US
Assignee:
Massachusetts Institute of Technology - Cambridge MA
International Classification:
G06N 3/08
G06N 3/04
G06F 17/14
G06F 17/16
Abstract:
A system for training a neural network model, the neural network model comprising a plurality of layers including a first hidden layer associated with a first set of weights, the system comprising at least one computer hardware processor programmed to perform: obtaining training data; selecting a unitary rotational representation for representing a matrix of the first set weights, the selected unitary rotational representation comprising a plurality of parameters; training the neural network model using the training data using an iterative neural network training algorithm to obtain a trained neural network model, each iteration of the iterative neural network training algorithm comprising: updating values of the plurality of parameters in the selected unitary rotational representation for representing the matrix of the set of weights for the at least one hidden layer, and saving the trained neural network model.