Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance
-
Updated
Apr 16, 2025 - Python
Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance
This repository contains code for the PhD thesis: "A Study of Self-training Variants for Semi-supervised Image Classification" and publications.
This project focuses on land use and land cover classification using Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The classification task aims to predict the category of land based on satellite or aerial images.
Lightweight neural network library written in ANSI-C supporting prediction and backpropagation for Convolutional- and Fully Connected neural networks
Artificial neural network package written in python
This repository contains benchmarking and comparison of the FFNN, RNN, and CNN on sequential and image data, alongwith using different optimizers for analyzing performance.
🧠 GAN Optimizer Benchmark Ce projet compare les performances de quatre algorithmes d'optimisation pour l'entraînement de GANs (Generative Adversarial Networks) sur le dataset CIFAR-10.
This is a Research of Various Optimization Algorithms that are used in ML and DL which is implemented on the 2 types of Dataset(Banglore_Housing & TSP)
ML Optimizer Visualizer Educational project comparing Gradient Descent, SGD, Momentum, RMSProp and Adam on the same 1D linear regression task. Features synthetic data with varying feature scales + noise to reveal real differences in optimizer behavior. Includes loss curves (linear & log), parameter trajectories and a clear performance summary
A fully vectorized Deep Neural Network (DNN) implementation built from scratch using only NumPy - no deep learning frameworks involved. Covers forward/backward propagation, activation functions, modular architecture, and training with different optimizers - a hands-on deep dive into the fundamentals of deep learning.
ECE-666: Applied Optimization methods for Machine Learning. This repository contains PyTorch implementations for a variety of recent optimization algorithms in deep learning.
Highly optimized computational geometry library (C++/CUDA) for manipulating 2D parametric curves for robotics
Add a description, image, and links to the rmsprop-optimizer topic page so that developers can more easily learn about it.
To associate your repository with the rmsprop-optimizer topic, visit your repo's landing page and select "manage topics."