A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...

The HSIC Bottleneck: Deep Learning without Back-Propagation

TensorFlow implementation of Barlow Twins (https://arxiv.org/abs/2103.03230).

Pytorch Implementation of the Nonlinear Information Bottleneck

Detecting Beneficial Feature Interactions for Recommender Systems, AAAI 2021

Project for the Large Scale Optimization course at Skoltech

[IEEE CISS 2024, ICMLW 2023] Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy

Implementation of the paper "MERINA+: Improving Generalization for Neural Video Adaptation via Information-Theoretic Meta-Reinforcement Learning" - N. Kan, et. al., 2023

The L0-SIGN implementation.

Deep Learning model training visualized using mutual information between the input and the output