Nature

Classification tasks using input driven nonlinear magnetization dynamics in spin Hall oscillator

The inherent nonlinear magnetization dynamics in spintronic devices make them suitable candidates for neuromorphic hardware. Among spintronic devices, spin torque oscillators such as spin transfer ...
Nature

Deep physical neural networks trained with backpropagation

However, implementing trained mathematical transformations by designing hardware for strict, operation-by-operation mathematical isomorphism is not the only way to perform efficient machine learning.
Visual Studio Magazine

Convolutional Neural Networks for MNIST Data Using PyTorch

Dr. James McCaffrey of Microsoft Research details the "Hello World" of image classification: a convolutional neural network (CNN) applied to the MNIST digits dataset. The "Hello World" of image ...
Visual Studio Magazine

Preparing MNIST Image Data Text Files

Dr. James McCaffrey of Microsoft Research demonstrates how to fetch and prepare MNIST data for image recognition machine learning problems. Many machine learning problems fall into one of three ...