Discover @tarek-ullah Open Source projects

H. M. Tarek Ullah (@tarek-ullah)

tarek-ullah

Stars
38
Global Rank 413,456 (Top 15 %)
Followers 4
Following 5
Registered over 7 years ago
Most used languages

C#
33.3 %

MATLAB
33.3 %

Python
33.3 %
Location 🇧🇩 Bangladesh
Country Total Rank 1,963
Country Ranking

MATLAB
29

C#
255

Python
512

AD-Detection-From-3D-Brain-MRI-Data-Using-Deep-Deterministic-Convolutional-Neural-Networks

This repository is related to the thesis paper titled as "ALzheimer's Disease & Dementia Detection From 3D Brain MRI Data Using Deep Convolutional Neural Networks." This thesis paper was accepted and published by IEEE's 3rd INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY ( I2CT), PUNE, INDIA - 6-8 APRIL, 2018.

Location-Based-Food-Delivery-Service-Using-Python-and-Google-Maps-APIs

Implementation of Location based food delivery service using Python 2.7 and Google Maps APIs.It suggests restaurants to users based on their location and choice of cuisine. Moreover it shows delivery time , distance of user from selected restaurant in km and also draws a shortest path in google Map using travelling salesman problem under the hood. in It's only the Back-End or just a console app without any database.

Point-Of-Sales

This project is developed in C# .In this project I have followed N-Tier architecture and also developed Object Relational Mapping (ORM ) from Scratch using MySQL database as backend . Metro UI has been used for user interface design.This project is useful for small shops.

Reinforcement-Learning-Algorithms

These implementatios shows Convergence and performance of policy and value iteration algorithms, how the convergence of these algorithms to the optimal value function depends on the number of iterations used. Furthermore, I have implemented on-policy SARSA and off-policy Q-learning algorithms and showed how the performance of these algorithms depends on the exploration-exploitation tradeoff, and on learning rates. My experiments were evaluted on benchmark reinforcement learning tasks such as a smallworld, gridworld and a cliffworld MDP to analyze the performance of our algorithms.