Build your own AI agent
Hemant Rakesh (~hemant56) |
Description:
Introduction
The term "Artificial Intelligence" is often used to describe machines (or computers) that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem solving". In this workshop I will be demonstrating the concept of reinforcement learning, which is one of the subcategories of AI. And currently the hottest topics in today's AI generation.
You may have noticed that computers can now automatically learn to play ATARI games (from raw game pixels!), they are beating world champions at Go, simulated quadrupeds are learning to run and leap, and robots are learning how to perform complex manipulation tasks that defy explicit programming.
The workshop
I hope have gotten you a bit something get excited about the content of the workshop, given the introduction.
This will be a hands-on workshop focused on developing your own reinforcement learning agent, which can play Ping-Pong or Mario or even Space invaders
The only requirements for this workshop is:
- A fully charged laptop and,
- Access to internet
The workshop is split into four parts:
- introduction to reinforcement learning (30 minutes)
- Types of agents and how to choose an environment (30 minutes)
- Mathematical explanation of the agent and it's behavior (30 minutes)
- Creative and innovative agent developing for predefined environments (30 minutes) [ Hands-on]
- Project: Build your own AI agent (30 minutes)
- Participants would have build their own AI with the environments.
Takeaway assignments will be based on the content of the workshop. For example, building an agent to complete a task in given number of moves or building a mario-like environment and develop an AI for the same.
These assignments will not only help understand the purpose of AI but also will help you implement the same in any of your future AI applications and lastly, help contribute in open source projects.
The assignments will be mailed to every participant after the workshop.
Duration: approximately 150 minutes
Prerequisites:
Mathematical Prerequisites:
- Basic Probability theory
- Basic Statistics
- Basic calculus (differentiation)
Technical Prerequisites:
Good knowledge of Python
Content URLs:
A few samples are in the following link:
Speaker Info:
Hemant Rakesh a final year CSE student at NMIT, Bangalore; has keen interests in deep learning and is a reinforcement learning enthusiast. With prior experience in this field he loves to share his skills and knowledge to the community as he believes - " together we grow ". He also heads the machine learning club at nmit and has authored quite a few AI based blogs on Medium.
Hemant is also a research intern currently working on projects with Biomedical Engineering(10^-6 - 10^9) and Electronic System, Indian Institute of Science, Bangalore. He has a rich experience in computer vision, deep learning, reinforcement learning, neural computing and medical imaging and EEG based computation. Also, he has experience in building software tools in python for Image and neural analysis.
Speaker Links:
A list of few of my blogs can be found as follows:
1 Introduction to Neural Networks
3 Distributed training using Tensorflow
LinkedIn: https://www.linkedin.com/in/hemant-rakesh-983b59129/
Github: https://github.com/Hemantr05/