BabyGPT: Build Your Own GPT Large Language Model from Scratch Pre-Training Generative Transformer Models: Building GPT from Scratch with a Step-by-Step Guide to Generative AI in PyTorch and Python

Bags of Tricks in OGB (node classification) with GCNs.

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs

CRNN/LPRNet/STNet + CTC + CCPD

Paper Name: Convolutional Neural Networks and Residual Connections for Cow Teat Image Classification. Testing the impact of Convolutional Neural layers and Residual Conections in the accuracy of dairy Cows Teat Imaga classification Dataset from and testing software: https://github.com/YoushanZhang/SCTL

Pytorch-based RAND implementation

Machine Learning Practical - Coursework 2: Analysing problems with the VGG deep neural network architectures (with 8 and 38 hidden layers) on the CIFAR100 dataset by monitoring gradient flow during training. And exploring solutions using batch normalization and residual connections.

This repository implements an Attention-based Residual LSTM model for earthquake return period prediction in Sulawesi. Using USGS data (1975-2024), it enhances accuracy with attention mechanisms and residual connections, mitigating vanishing gradients. The model improves seismic forecasting, aiding disaster preparedness and risk mitigation.

Machine Learning Practical - Coursework 2 Report: Analysing problems with the VGG deep neural network architectures (with 8 and 38 hidden layers) on the CIFAR100 dataset by monitoring gradient flow during training. And exploring solutions using batch normalization and residual connections.

This repo is about an image enhancement