Reproducing the paper "PADAM: Closing The Generalization Gap of Adaptive Gradient Methods In Training Deep Neural Networks" for the ICLR 2019 Reproducibility Challenge

A compressed adaptive optimizer for training large-scale deep learning models using PyTorch

Simple MATLAB toolbox for deep learning network: Version 1.0.3

Implement different variants of gradient descent in python using numpy

Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance

Deep Learning Optimizers

Implementation and comparison of SGD, SGD with momentum, RMSProp and AMSGrad optimizers on the Image classification task using MNIST dataset

flexible and extensible implementation of a multithreaded feedforward neural network in Java including popular optimizers, wrapped up in a console user interface

CNeuron is a simple singular neural network neuron implementation in C, designed for easy integration into C projects.

Implementation of a 3 layer neural net in numpy, trained and tested on MNIST dataset

Using different optimizers for a comparison study, finding the root of differences by visualization and to find the best case for a specific task

This project was developed as part of the Biologically Inspired Artificial Intelligence course at the Silesian University of Technology. The goal is to automatically classify eye diseases (diabetic retinopathy, cataract, glaucoma, normal) from retinal images using a convolutional neural network (CNN) inspired by the human visual cortex.

Analyzed the mathematical intuition and real-world performance of SGD + Momentum, Adagrad, and RMSprop optimizers. Implemented SMOTE and trained a deep neural network to address imbalanced datasets.

Week 1 assignment form Coursera's "Advanced Machine Learning - Introduction to Deep Learning"

Advance Machine Learning (CSL 712) Course Lab Assignments