← Search

Charles Windolf

2 accepted papers

2020

A Biologically Plausible Neural Network for Slow Feature Analysis

NeurIPS 2020poster

Learning latent features from time series data is an important problem in both machine learning and brain function. One approach, called Slow Feature Analysis (SFA), leverages the slowness of many salient features relative to the rapidly varying input signals. Furthermore, when trained on naturalist…

2018

Learning long-range spatial dependencies with horizontal gated recurrent units

NeurIPS 2018poster

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human accuracy on a variety of visual recognition tasks. Here, how…