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

▶
1
SMART_READER_LITE
LIVE PREVIEW

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

Feb 18, 2023 478 likes •807 views

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?

slide-1
SLIDE 1

Deep Reinforcement Learning

Qianqian Li, Nayeon Koong, Langtian He

1

slide-2
SLIDE 2

What is deep reinforcement learning?

Agent/Actor + Action + Environment + State + Reward

slide-3
SLIDE 3

How does reinforcement learning work?

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

slide-4
SLIDE 4

Winning Atari Breakout

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

slide-5
SLIDE 5

Beating people in dozens of computer games

http://www.yaronhadad.com/deep-learning-most-amazing-applications/

slide-6
SLIDE 6

Robotics

slide-7
SLIDE 7

AlphaGo AI program wins $1 million prize in Go showdown with champion Lee Sedol

Credit: Google DeepMind via YouTube

slide-8
SLIDE 8

Speculation/Emerging Technologies

Smart Prosthetic Limbs

slide-9
SLIDE 9

Autonomous Robots

slide-10
SLIDE 10

Machine Learning

2

slide-11
SLIDE 11

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.

slide-12
SLIDE 12

AI vs Machine learning

mimicking human abilites vs

subset of AI that trains a machine how to learn

slide-13
SLIDE 13

Algorithms

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

slide-14
SLIDE 14
slide-15
SLIDE 15

Users

Health care Oil and gas Government Marketing and sales

slide-16
SLIDE 16

Why is it important?

As models are exposed to new data, they are able to independently adapt. Tiey learn from previous computations to produce reliable, repeatable decisions and results.

slide-17
SLIDE 17

Speculation

Prolonging a mobile device’s battery

slide-18
SLIDE 18

Cognitive Computing 3

slide-19
SLIDE 19

Definition

slide-20
SLIDE 20

What is Cognitive computing (CC) ?

slide-21
SLIDE 21
slide-22
SLIDE 22

Cognitive Computing = Artificial Intelligence?

slide-23
SLIDE 23

Use Cases

slide-24
SLIDE 24

IBM Watson

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

slide-25
SLIDE 25

Ross intelligence

slide-26
SLIDE 26

Donna

slide-27
SLIDE 27

Speculation

slide-28
SLIDE 28

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.

slide-29
SLIDE 29

Retail:

  • help identify buying patterns, preferences, insights …
slide-30
SLIDE 30

Transportation:

  • make realtime decisions about the environment
slide-31
SLIDE 31

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