Yashwanth Reddy Virupaksha's Projects
Lane detection using computer vision algorithms
Using Capsule Networks to perform classification of different Pokemon's
PDFsam, a desktop application to extract pages, split, merge, mix and rotate PDF files
Deep Learning models on various databases
A deep learning library to rank protein complexes using graph neural networks
A deep learning library for graph data structures
The Reinforcement Learning problem can be improved in certain circumstances by creating a Model neural network to learn the dynamics of the real environment and learn by experimenting in the Model environment instead of Real environment.
The OpenMined Unity Application
The contextual Bandit problem is the intermediate between Simple Bandit problem and the full RL problem. In this experiment we are going to find optimal policy to obtain maximum rewards.
This experiment learns the optimal policies by the method of Policy-Gradients in the Full Reinforcement Learning problem in the environment "CartPole" from OpenAI Gym.
With the concept of Policy Gradients in Reinforcement Learning we are going find optimal policy for obtaining maximum reward in Multi-armed Bandit Problem
This project is a PyTorch rewrite of the ML library “Basset”
Private Deep Learning Client
With the concept of Q-Learning using Neural Networks in Reinforcement Learning we are going to experiment in the environment "FrozenLake" provided by OpenAI Gym
With the concept of Q-Table learning in Reinforcement Learning we are going to experiment in the environment "FrozenLake" provided by OpenAI Gym
Build a Jekyll blog in minutes, without touching the command line.