General Unitary Neural Network

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.

Researchers

Scott Skirlo / Yichen Shen / Tena Dubcek / Li Jing / John Peurifoy / Max Tegmark / Marin Soljacic

Departments: Department of Physics
Technology Areas: Artificial Intelligence (AI) and Machine Learning (ML) / Computer Science: Networking & Signals

  • systems and methods for training neural networks
    Patent Cooperation Treaty | Published application
  • systems and methods for training neural networks
    United States of America | Published application

License this technology

Interested in this technology? Connect with our experienced licensing team to initiate the process.

Sign up for technology updates

Sign up now to receive the latest updates on cutting-edge technologies and innovations.