JAX compilation of RDDL description files, and a differentiable planner in JAX.

A header-only C++ Library for Optimization Algorithms

Our project utilizes machine learning models to predict cardiovascular diseases (CVDs) by analyzing diverse datasets and exploring 14 different algorithms. The aim is to enable early detection, personalized interventions, and improved healthcare outcomes.

AutoSGM

Repository contains my MATLAB files for the hand-coded MNIST (w/ SGD optimizer) classification model trained for the EEL5813 - Neural Networks: Algorithms and Applications course, PROJECT02

Stanford-CS221 class practical's, Assignments and projects

XCSF learning classifier system: rule-based online evolutionary machine learning

Optimalization – finding parameters of linear regression using various algorithms

Dynamically adjusts load balancers coupled with auto scalers in response to workload changes using weakly coupled Markov Decision Processes (MDPs) and a two-timescale online learning approach.

A proof of concept of a recursion doing stochastic gradient descent for a simple neural network. Done in Python3 with numpy

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.

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

recommender systems algorithms

Parametric estimation of multivariate Hawkes processes with general kernels.

The ability to predict prices and features affecting the appraisal of property can be a powerful tool in such a cash intensive market for a lessor. Additionally, a predictor that forecasts the number of reviews a specific listing will get may be helpful in examining elements that affect a property's popularity.

A basic neural network with backpropagation programmed from scratch in C++

Logistic Regression with different optimizers in Python from scratch

Easy-to-use linear and non-linear solver

This code uses computational graph and neural network to solve the five-layer traffic demand estimation in Sioux Falls network. It also includes comparison of models and 10 cross-validations.