Irina Rish

Beyond Backprop: Alternating Minimization with co-Activation Memory.

2018 · arXiv (Cornell University)

Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error backpropagation, which suffers from several well-known issues, …

SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization

2021 · arXiv (Cornell University)

A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data distribution is not i.i.d to the training domains. This failure often stems from learning …

MEEGNet: An open source python library for the application of convolutional neural networks to MEG

2025 · bioRxiv (Cold Spring Harbor Laboratory)

Abstract Artificial Neural Networks (ANNs) are rapidly gaining traction in neuroscience, proving invaluable for decoding and modeling brain signals from techniques such as electroencephalography (EEG) and functional magnetic resonance imaging (fMRI). Although these networks are …