A next-gen solver for optimization with nonconvex objective and constraints. Reimplements filterSQP and IPOPT (barrier) in a modern and generic way, and unlocks a variety of novel methods. Competitive against filterSQP, IPOPT, SNOPT, MINOS and CONOPT.

This repository consist of machine learning models which can be use for predicting the future instance. More specifically this repository is a Machine Learning course for those who are interested in learning the basics of machine learning algorithms.

Deep Learning with PyTorch

This toolkit is a curated collection of machine learning projects, resources, and utilities designed to assist both beginners and seasoned practitioners in their journey through the fascinating world of machine learning.

Optimizing neural networks is crucial for achieving high performance in machine learning tasks. Optimization involves adjusting the weights and biases of the network to minimize the loss function. This process is essential for training deep learning models effectively and efficiently.

University assignments and sandbox projects connected to machine learning study.

Github repo for ML Specialization course on Coursera. Contains notes and practice python notebooks.

Implementation from scratch (using numpy arrays) of a framework based on keras interface which allows to build and train Fully Connected Networks and Convolutional Neural Networks (CNNs).

Heavy-tailed ESD without gradient noise

Linear Algebra_Assignment

Gradient Descent Optimizers and Genetic Algorithms using GPUs, CPUs, and FPGAs via CUDA, OpenCL, and oneAPI

practical work completed during the first year of the Master 1 in Artificial Intelligence

Official code for the paper "Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent"

This project will cover some of the basic Artificial Intelligence along the course using Python. Mainly will use Numpy to build everything. I write all the files in Python and it refers back to the school labs at Dalhousie University.

Custom implementation of a neural network from scratch using Python

Introduction to Python and Neural Network with Keras and PyTorch for beginners

Modern C++ port of the Limited-memory BFGS (L-BFGS) optimization algorithm