Public code of the ML course

Repository holding various implementation of specific NMF methods for speaker diarization

Ordered Weighted L1 regularization for classification and regression in Python

A package for AFM image reconstruction and compressed sensing in general

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

Sparseout: Controlling Sparsity in Deep Networks

"The Unreasonable Effectiveness of Sparse Dynamic Synapses for Continual Learning" paper project.

A pure implementation for sparse denoising autoencoder with adaptive evolutionary training using Scipy. The sparse implementation makes the algorithm scalable to high dimensional data and trainable on CPUs.

Attention-Based Guided Structured Sparsity of Deep Neural Networks

Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On i…

Sparse Recurrent Neural Networks -- Pruning Connections and Hidden Sizes (TensorFlow)

Sparse and structured neural attention mechanisms

Overparameterization and overfitting are common concerns when designing and training deep neural networks. Network pruning is an effective strategy used to reduce or limit the network complexity, but often suffers from time and computational intensive procedures to identify the most important connections and best performing hyperparameters. We s…

Robust Single Sample Face Recognition by Sparsity-Driven Sub-Dictionary Learning Using Deep Features

Network Slimming (Pytorch) (ICCV 2017)

A new efficient subspace and K-Means clustering based method to improve Collaborative Filtering

Official PyTorch (Lightning) implementation of the NeurIPS 2020 paper "Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity".

Minimal Reproducibility Study of (https://arxiv.org/abs/1911.05248). Experiments with Compression of Deep Neural Networks

Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).

Understanding the effects of data parallelism and sparsity on neural network training