a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results

[NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.

The is the official implementation of ICML 2023 paper "Revisiting Weighted Aggregation in Federated Learning with Neural Networks".

Advanced CIFAR-10 image classification using ResNet-inspired CNN with residual blocks, achieving 92%+ accuracy through comprehensive regularization, data augmentation, and professional ML engineering practices.

Investigating the Role of Weight Decay in Enhancing Nonconvex SGD, CVPR 2025

Super-Convergence on CIFAR10

Implementation of some new techniques from fastai and other papers which works with keras models

Machine Learning university project

Folder contains implementation of Multi layer feed forward networks, Autoencoders, Sparse Autoencoders and many..