An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Using Teacher Assistants to Improve Knowledge Distillation: https://arxiv.org/pdf/1902.03393.pdf

[ICML 2018] "Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions"

Tools and libraries to run neural networks in Minecraft ⛏️

[ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Zhangyang Wang

Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)

[ICLR 2023] Pruning Deep Neural Networks from a Sparsity Perspective

Bayesian Optimization-Based Global Optimal Rank Selection for Compression of Convolutional Neural Networks, IEEE Access

Code for testing DCT plus Sparse (DCTpS) networks

Official PyTorch implementation of "Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming" (ICML'23)

Compact representations of convolutional neural networks via weight pruning and quantization

Code for our WACV 2021 paper "Exploiting the Redundancy in Convolutional Filters for Parameter Reduction"

ESPN: Extreme Sparse Pruned Network

Neural Network Pruning Using Dependency Measures

Image classification using compressed deep neural network ported on resource-constrained platforms.

This repository is for reproducing the results shown in the NNCodec ICML Workshop paper. Additionally, it includes a demo, prepared for the Neural Compression Workshop (NCW).

Development and Evaluation of Neural Net Sensitivity-Based Pruning Algorithms Using Statistical Inference

Compressed CNNs for airplane classification in satellite images (APoZ-based parameter pruning, INT8 weight quantization)

Use a meta-network to learn the importance and correlation of neural network weights