1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian - PowerPoint PPT Presentation

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He

What is deep reinforcement learning? Agent/Actor + Action + Environment + State + Reward

How does reinforcement learning work? https://medium.com/@BonsaiAI/deep-reinforcement-learning-from-toys-to-enteprise-147d990ea381

Winning Atari Breakout Image from https://github.com/kuz/DeepMind-Atari-Deep-Q-Learner

Beating people in dozens of computer games http://www.yaronhadad.com/deep-learning-most-amazing-applications/

Robotics

AlphaGo AI program wins $1 million prize in Go showdown with champion Lee Sedol Credit: Google DeepMind via YouTube

Speculation/Emerging Technologies Smart Prosthetic Limbs

Autonomous Robots

2 Machine Learning

What is it? Machine learning(ML) is a method of data analysis that automates ana- lytical model building. Systems can learn from data, identify patterns and make decisions with human intervention.

AI vs Machine learning mimicking human abilites vs subset of AI that trains a machine how to learn

Algorithms Algorithms enables real-time processing of large amount of data, and de- liver accurate predictions.

Users Health care Oil and gas Government Marketing and sales

Why is it important? As models are exposed to new data, they are able to independently adapt. Ti ey learn from previous computations to produce reliable, repeatable decisions and results.

Speculation Prolonging a mobile device’s battery

3 Cognitive Computing

Definition

What is Cognitive computing (CC) ?

Cognitive Computing = Artificial Intelligence?

Use Cases

IBM Watson https://www.youtube.com/watch?v=WFR3lOm_xhE

Ross intelligence

Donna

Speculation

Consider these statistics: - 2.5 Quintillion bytes of data created every day. - 90% of the data in the world today has been created in the last two years alone. - Every minute 1.7 MB of data is created for every person on the planet. All 7.3 billion of us.

Retail: - help identify buying patterns, preferences, insights … -

Transportation: - make realtime decisions about the environment

Computing will never rob man of his initiative or replace the need for creative thinking. By freeing man from the more menial or repetitive forms of thinking, computers will actually increase the opportunities for the full use of human reason. —— Thomas J. Watson, Jr