Artificial Intelligence A-Z Learn How To Build An AI

10/2017
16.5 hours

Welcome to the course!
02:31
Introduction
Preview
01:44
Where to get the Materials
00:08
BONUS: Meet Your Instructors
Preview
00:39
–
———- Part 0 – Fundamentals Of Reinforcement Learning ———-
01:15
Welcome to Part 0 – Fundamentals of Reinforcement Learning
01:15
–
Q-Learning Intuition
02:02:56
Plan of Attack
04:03
What is reinforcement learning?
Preview
11:26
The Bellman Equation
18:25
The “Plan”
02:12
Markov Decision Process
16:26
Policy vs Plan
12:55
Adding a “Living Penalty”
Preview
09:47
Q-Learning Intuition
14:45
Temporal Difference
19:26
Q-Learning Visualization
13:31
–
———- Part 1 – Self-Driving Car (Deep Q-Learning) ———-
00:50
Welcome to Part 1 – Self-Driving Car (Deep Q-Learning)
00:50
–
Deep Q-Learning Intuition
55:46
Plan of Attack
02:17
Deep Q-Learning Intuition – Learning
15:15
Deep Q-Learning Intuition – Acting
06:06
Experience Replay
15:45
Action Selection Policies
16:23
–
Installation for Part 1
35:09
Plan of Attack (Practical Tutorials)
00:29
Where to get the Materials
00:08
Windows Option 1: End-to-End installation steps
00:42
Windows Option 2 – Part A: Installing Ubuntu on Windows
14:07
Windows Option 2 – Part B: Installing PyTorch and Kivy on your Ubuntu VM
00:11
Mac or Linux: Installing Anaconda
07:08
Mac or Linux: Installing PyTorch and Kivy
06:42
Getting Started
05:41
–
Creating the environment
25:33
Self Driving Car – Step 1
Preview
09:15
Self Driving Car – Step 2
16:18
–
Building an AI
02:17:27
Self Driving Car – Step 3
06:44
Self Driving Car – Step 4
14:23
Self Driving Car – Step 5
05:59
Self Driving Car – Step 6
06:01
Self Driving Car – Step 7
05:46
Self Driving Car – Step 8
10:51
Self Driving Car – Step 9
17:27
Self Driving Car – Step 10
13:51
Self Driving Car – Step 11
15:21
Self Driving Car – Step 12
12:57
Self Driving Car – Step 13
12:27
Self Driving Car – Step 14
02:53
Self Driving Car – Step 15
05:28
Self Driving Car – Step 16
07:19
–
Playing with the AI
27:05
Self Driving Car – Level 1
08:51
Self Driving Car – Level 2
Preview
04:39
Self Driving Car – Level 3
07:21
Self Driving Car – Level 4
06:08
Challenge Solutions
00:06
–
———- Part 2 – Doom (Deep Convolutional Q-Learning) ———-
00:28
Welcome to Part 2 – Doom (Deep Convolutional Q-Learning)
00:28
–
Deep Convolutional Q-Learning Intuition
19:16
Plan of Attack
03:26
Deep Convolutional Q-Learning Intuition
07:12
Eligibility Trace
08:38
–
Installation for Part 2
00:44
Where to get the Materials
00:08
Installing Open AI Gym and ppaquette
00:36
–
Building an AI
02:33:30
Doom – Step 1
05:54
Doom – Step 2
09:42
Doom – Step 3
09:52
Doom – Step 4
12:32
Doom – Step 5
14:16
Doom – Step 6
06:32
Doom – Step 7
04:40
Doom – Step 8
06:38
Doom – Step 9
03:44
Doom – Step 10
07:50
Doom – Step 11
06:33
Doom – Step 12
04:14
Doom – Step 13
06:49
Doom – Step 14
15:32
Doom – Step 15
08:27
Doom – Step 16
10:37
Doom – Step 17
19:38
–
Playing with the AI
19:21
Watching our AI play Doom
Preview
19:21
–
———- Part 3 – Breakout (A3C) ———-
00:26
Welcome to Part 3 – Breakout (A3C)
00:26
–
A3C Intuition
57:38
Plan of Attack
03:39
The three A’s in A3C
04:44
Actor-Critic
06:36
Asynchronous
11:42
Advantage
15:21
LSTM Layer
15:36
–
Installation for Part 3
00:08
Installing OpenCV
00:08
–
Building an AI
02:30:11
Breakout – Step 1
10:07
Breakout – Step 2
08:01
Breakout – Step 3
12:24
Breakout – Step 4
13:10
Breakout – Step 5
10:32
Breakout – Step 6
11:46
Breakout – Step 7
07:46
Breakout – Step 8
11:30
Breakout – Step 9
11:31
Breakout – Step 10
08:05
Breakout – Step 11
05:06
Breakout – Step 12
15:39
Breakout – Step 13
08:22
Breakout – Step 14
05:21
Breakout – Step 15
10:51
–
Annex 1: Artificial Neural Networks
01:30:11
What is Deep Learning?
12:34
Plan of Attack
02:51
The Neuron
16:15
The Activation Function
08:29
How do Neural Networks work?
12:47
How do Neural Networks learn?
12:58
Gradient Descent
10:12
Stochastic Gradient Descent
08:44
Backpropagation
05:21
–
Annex 2: Convolutional Neural Networks
01:40:47
Plan of Attack
03:31
What are convolutional neural networks?
15:49
Step 1 – Convolution Operation
16:38
Step 1(b) – ReLU Layer
06:41
Step 2 – Pooling
14:13
Step 3 – Flattening
01:52
Step 4 – Full Connection
19:24
Summary
04:19
Softmax & Cross-Entropy
18:20