English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 129 lectures (15h 26m) | 5.82 GB
Combine the power of Data Science, Machine Learning and Deep Learning to create powerful AI for Real-World applications!
Learn key AI concepts with intuition lectures to get you quickly up to speed with all things AI and practice them by building 7 different AIs:
- Build an AI with a Q-Learning model and train it to optimize warehouse flows in a Process Optimization case study.
- Build an AI with a Deep Q-Learning model and train it to land on the moon.
- Build an AI with a Deep Convolutional Q-Learning model and train it to play the game of Pac-Man.
- Build an AI with an A3C (Asynchronous Advantage Actor-Critic) model and train it to fight Kung Fu.
- Build an AI with a PPO (Proximal Policy Optimization) model and train it for a Self-Driving Car.
- Build an AI with a SAC (Soft Actor-Critic) model and train it for a Self-Driving Car.
- Build an AI by fine-tuning a powerful pre-trained LLM (Llama 2 by Meta) with Hugging Face and re-train it to chat with you about medical terms. Simply put, we build here an AI Doctor Chatbot.
But that’s not all… Once you complete the course, you will get 3 extra AIs: DDPG, Full World Model, and Evolution Strategies & Genetic Algorithms. We build these AIs with ChatGPT for a Self-Driving Car and a Humanoid application. For each of these extra AIs you will get a long video lecture explaining the implementation, a mini PDF, and the Python code.
Besides, you will get a free 3-hour extra course on Generative AI and LLMs with Cloud Computing as a Prize for completing the course.
What you’ll learn
- Build 7 different AIs for 7 different applications
- Understand the theory behind Artificial Intelligence
- Master the State of the Art AI models
- Solve Real World Problems with AI
- Q-Learning
- Deep Q-Learning
- Deep Convolutional Q-Learning
- A3C (Asynchronous Advantage Actor-Critic)
- PPO (Proximal Policy Optimization)
- SAC (Soft Actor-Critic)
- LLMs
- Transformers
- Low-Rank Adaptation (LoRA) and Quantization (QLoRA)
- NLP techniques for Chatbots: Tokenization and Padding
- Fine-Tuning an LLM with Knowledge Augmentation
- As Extras: DDPG, Full World Model, Evolution Strategies & Genetic Algorithms
Table of Contents
Welcome to the course
1 Welcome Challenge
2 Why AI
3 Hello from Hadelin
4 Quick Win Build a ChatBot app that speaks like Master Yoda
5 Course Structure Codes Additional Reading and PDF
6 EXTRA Use ChatGPT to Build AI More Efficiently
Part 0 Fundamentals Of Reinforcement Learning
7 Welcome to Part 0 Fundamentals of Reinforcement Learning
QLearning Intuition
8 Plan of Attack
9 What is reinforcement learning
10 The Bellman Equation
11 The Plan
12 Markov Decision Process
13 Policy vs Plan
14 Adding a Living Penalty
15 QLearning Intuition
16 Temporal Difference
QLearning Implementation
17 A QLearning Implementation for Process Optimization
Part 1 Deep QLearning
18 Welcome to Part 1 Deep QLearning
Deep QLearning Intuition
19 Plan of Attack
20 Deep QLearning Intuition Learning
21 Deep QLearning Intuition Acting
22 Experience Replay
23 Action Selection Policies
Deep QLearning Implementation
24 Welcome to the Practical Activity of Part 1
25 Get the Codes here
26 Deep QLearning Implementation Step 1
27 Deep QLearning Implementation Step 2
28 Deep QLearning Implementation Step 3
29 Deep QLearning Implementation Step 4
30 Deep QLearning Implementation Step 5
31 Deep QLearning Implementation Step 6
32 Deep QLearning Implementation Step 7
33 Deep QLearning Implementation Step 8
34 Deep QLearning Implementation Step 9
35 Deep QLearning Implementation Step 10
36 Deep QLearning Implementation Step 11
37 Deep QLearning Implementation Step 12
38 Deep QLearning Implementation Step 13
39 Deep QLearning Implementation Step 14
40 Deep QLearning Implementation Step 15
41 Deep QLearning Implementation Step 16
42 Deep QLearning Implementation Step 17
43 Deep QLearning Implementation Step 18
44 Deep QLearning Implementation Step 19
45 video
46 Deep QLearning Implementation Step 20
Part 2 Deep Convolutional QLearning
47 Welcome to Part 2 Deep Convolutional QLearning
Deep Convolutional QLearning Intuition
48 Plan of Attack
49 Deep Convolutional QLearning Intuition
50 Eligibility Trace
Deep Convolutional QLearning Implementation
51 Welcome to the Practical Activity of Part 2
52 Get the Codes here
53 Deep Convolutional QLearning Implementation Step 1
54 Deep Convolutional QLearning Implementation Step 2
55 Deep Convolutional QLearning Implementation Step 3
56 Deep Convolutional QLearning Implementation Step 4
57 Deep Convolutional QLearning Implementation Step 5
58 Deep Convolutional QLearning Implementation Step 6
59 Deep Convolutional QLearning Implementation Step 7
60 Deep Convolutional QLearning Implementation Step 8
61 Deep Convolutional QLearning Implementation Step 9
62 Deep Convolutional QLearning Implementation Step 10
63 Deep Convolutional QLearning Implementation Step 11
64 Deep Convolutional QLearning Implementation Step 12
65 video
66 Deep Convolutional QLearning Implementation Step 13
Part 3 A3C
67 Welcome to Part 3 A3C
A3C Intuition
68 Plan of Attack
69 The three As in A3C
70 ActorCritic
71 Asynchronous
72 Advantage
73 LSTM Layer
A3C Implementation
74 Welcome to the Practical Activity of Part 3
75 Get the Codes here
76 A3C Implementation Step 1
77 A3C Implementation Step 2
78 A3C Implementation Step 3
79 A3C Implementation Step 4
80 A3C Implementation Step 5
81 A3C Implementation Step 6
82 A3C Implementation Step 7
83 A3C Implementation Step 8
84 A3C Implementation Step 9
85 A3C Implementation Step 10
86 A3C Implementation Step 11
87 A3C Implementation Step 12
88 A3C Implementation Step 13
89 A3C Implementation Step 14
90 video
91 A3C Implementation Step 15
Part 4 PPO and SAC
92 Welcome to the Practical Activity of Part 4
93 Build and Train the PPO and SAC models for a SelfDriving Car Theory included
Part 5 Intro to Large Language Models LLMs
94 Welcome to Part 5 Intro to Large Language Models LLMs
LLMs Intuition
95 Introduction to LLMs
96 Ingredients of an LLM
97 Who invented LLMs
98 How LLMs generate text
99 Inside an LLM Under the Hood
100 LLM Parameters
101 LLM Context Window
102 FineTuning LLMs
LLMs Implementation
103 Welcome to the Practical Activity of Part 5
104 Get the Codes here
105 FineTuning LLMs with Hugging Face Step 1
106 FineTuning LLMs with Hugging Face Step 2
107 FineTuning LLMs with Hugging Face Step 3
108 FineTuning LLMs with Hugging Face Step 4
109 FineTuning LLMs with Hugging Face Step 5
110 FineTuning LLMs with Hugging Face Step 6
111 FineTuning LLMs with Hugging Face Step 7
THANK YOU
112 THANK YOU Video
Annex 1 Artificial Neural Networks
113 What is Deep Learning
114 Plan of Attack
115 The Neuron
116 The Activation Function
117 How do Neural Networks work
118 How do Neural Networks learn
119 Gradient Descent
120 Stochastic Gradient Descent
121 Backpropagation
Annex 2 Convolutional Neural Networks
122 Plan of Attack
123 What are convolutional neural networks
124 Step 1 Convolution Operation
125 Step 1b ReLU Layer
126 Step 2 Pooling
127 Step 3 Flattening
128 Step 4 Full Connection
129 Summary
130 Softmax CrossEntropy
Congratulations Dont forget your Prize
131 Huge Congrats for completing the challenge
132 Bonus How To UNLOCK Top Salaries Live Training
Resolve the captcha to access the links!