← Search

Theodore Willke

2 accepted papers

2020

Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network

ICML 2020poster

Recent work has shown that topological enhancements to recurrent neural networks (RNNs) can increase their expressiveness and representational capacity. Two popular enhancements are stacked RNNs, which increases the capacity for learning non-linear functions, and bidirectional processing, which expl…

2018

Matrix-normal models for fMRI analysis

AISTATS 2018poster

Multivariate analysis of fMRI data has bene- fited substantially from advances in machine learning. Most recently, a range of prob- abilistic latent variable models applied to fMRI data have been successful in a variety of tasks, including identifying similarity pat- terns in neural data, combining…