asokraju

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

gpt-pilot

The first real AI developer

AI-Expert-Roadmap

Roadmap to becoming an Artificial Intelligence Expert in 2022

optuna

A hyperparameter optimization framework

deep-image-prior

Image restoration with neural networks but without learning.

nlp-roadmap

ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP

neural-style-tf

TensorFlow (Python API) implementation of Neural Style

Deep-Reinforcement-Learning-Hands-On

Hands-on Deep Reinforcement Learning, published by Packt

garage

A toolkit for reproducible reinforcement learning research.

d3rlpy

An offline deep reinforcement learning library

ctci-python-solutions

Cracking the Coding Interview in Python 3. The solutions all have detailed explanations with visuals.

AI-basketball-analysis

:basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.

Stocksera

Finance application that provides more than 60 different alternative data to retail investors

Reinforcement_Learning

Reinforcement learning tutorials

Lessons-Learned-Data-Science-Interviews

Lessons learned the hard way through over 30+ data science interviews

python_visualization_tutorial

A comprehensive guide of how to make publication-ready figures in python

TRPO-Tensorflow2

TRPO Implementation in Tensorflow 2.0 for Reinforcement Learning Project @ Sapienza

Adv-MARL

Adversarial attacks in consensus-based multi-agent reinforcement learning

gym-opendss

An implementation of an OpenAI gym environment for EPRI OpenDSS, using OpenDSS's native Python COM interface.

kristools

Clustor deployable custom DDPG algorithm for Multi Agent RL impleted in Tensorflow

jhepc

John Hunter Excellence in Plotting Contest

David_Silver

I have implemented the examples presented in David silver's lectures on Ipython notebooks. They can be opened through google colab.

ml-grinding

Rienforcement-learning-Algorithms

Generative-Terrain-Reconstruction

Using GAN to generate Terrain from LiDAR data

pm-motor-nonlinear-control

This function generates the response time optimal controller parameters for a permanent magnet motor, resulting in zero torque ripple under no measurement noise.

DC2DC-PowConv

Titanic

EDA and ML

num-tri

This code generates the special number triangles in any base representation.

papr-opt

This function searches (brute search) for the optimal Gray coded map resulting in least PAPR.