AI A-Z [2026]: Agentic AI, Gen AI, Prompt Engineering and RL

Combine the power of Agentic AI, Generative AI, Prompt Engineering and Deep RL to build powerful AIs with AWS and Python

  • 0.0 (0 Reviews)
  • 0 Students
  • 164 Lessons
  • Hadelin de Ponteves

Course Overview

Welcome to Artificial Intelligence A-Z!


This course is structured in 10 parts:


  1. Part 1 - Prompt Engineering: Prompt Engineering & Prompt Templates, Prompt Engineering Techniques, The 4 Elements of a (good) prompt, Inference Parameters

  2. Part 2 - Generative AI: Fundamentals of Generative AI, Image Generation, Foundation Models Overview, Foundation Models Lifecycle, Data Selection, Foundation Models Selection, Training vs. Inference, Context Window, Tokens and Embeddings, Transformers, Foundation Models Training, Foundation Models Fine-Tuning, Foundation Models Evaluation, Retrieval-Augmented Generation (RAG) for Cooking Assistance

  3. Part 3 - Agentic AI: AI Agents, Building a Cloud-powered AI Agent for Business Assistance

  4. Part 4 - Fundamentals of Reinforcement Learning: Q-Learning Intuition, Q-Learning Implementation

  5. Part 5 - Deep Q-Learning: Deep Q-Learning Intuition, Deep Q-Learning Implementation for Moon Landing

  6. Part 6 - Deep Convolutional Q-Learning: Deep Convolutional Q-Learning Intuition, Deep Convolutional Q-Learning Implementation for Pac-Man

  7. Part 7 - A3C: A3C Intuition, A3C Implementation for Kung Fu

  8. Part 8 - PPO and SAC: Proximal Policy Optimization, Soft Actor-Critic, Build and Train the PPO & SAC models for Self-Driving Cars

  9. Part 9 - LLMs: The Ingredients of an LLM, Who invented LLMs, How LLMs generate text, Understand what's inside an LLM, The LLM Parameters, The LLM Context Window, How to Fine-Tune LLMs for Medical Assistance

  10. Part 10 - Responsible AI: Features of Responsible AI, Guardrails in Generative AI, Legal Risks of Generative AI, AWS Tools for Responsible AI, Amazon SageMaker Clarify and Monitor, Amazon Augmented AI [Amazon A2I], Interpretability vs. Explainability, SageMaker Model Cards


All along this journey, you will learn key AI concepts with intuition lectures to get you quickly up to speed with all things AI and practice them by building 12 different AIs:


  1. Build a ChatBot App that speaks like Master Yoda in 5 Minutes.

  2. Build a Movie Script Generator by leveraging advanced Prompt Engineering.

  3. Build Your Custom LLM with Amazon Bedrock, Databricks, and Hugging Face.

  4. Build a RAG-powered Generative AI application with Amazon Bedrock and Knowledge Bases.

  5. Build an AI Agent with a Foundation Model (LLM) for business assistance, all powered by the Cloud.

  6. Build an AI with a Q-Learning model and train it to optimize warehouse flows in a Process Optimization case study.

  7. Build an AI with a Deep Q-Learning model and train it to land on the moon.

  8. Build an AI with a Deep Convolutional Q-Learning model and train it to play the game of Pac-Man.

  9. Build an AI with an A3C (Asynchronous Advantage Actor-Critic) model and train it to fight Kung Fu.

  10. Build an AI with a PPO (Proximal Policy Optimization) model and train it for a Self-Driving Car.

  11. Build an AI with a SAC (Soft Actor-Critic) model and train it for a Self-Driving Car.

  12. Build an AI by fine-tuning a powerful pre-trained LLM (Llama 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.


Some of these AIs will be built in AWS, and the others will be built in Python and PyTorch.


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.


And last but not least, here is what you will get with this course:


1. Complete beginner to expert AI skills: Learn to code self-improving AI for a range of purposes. In fact, we code together with you. Every tutorial starts with a blank page and we write up the code from scratch. This way you can follow along and understand exactly how the code comes together and what each line means.

2. Hassle-Free Coding and Code templates: We will build all our AIs in Google Colab, which means that we will have absolutely NO hassle installing libraries or packages because everything is already pre-installed in Google Colab notebooks. Plus, you’ll get downloadable Python code templates (in .py and .ipynb) for every AI you build in the course. This makes building truly unique AI as simple as changing a few lines of code. If you unleash your imagination, the potential is unlimited.

3. Intuition Tutorials: Where most courses simply bombard you with dense theory and set you on your way, we believe in developing a deep understanding for not only what you’re doing, but why you’re doing it. That’s why we don’t throw complex mathematics at you, but focus on building up your intuition in AI for much better results down the line.

4. Real-world solutions: You’ll achieve your goal in not only one AI model but in 5. Each module is comprised of varying structures and difficulties, meaning you’ll be skilled enough to build AI adaptable to any environment in real life, rather than just passing a glorified memory “test and forget” like most other courses. Practice truly does make perfect.

5. In-course support: We’re fully committed to making this the most accessible and results-driven AI course on the planet. This requires us to be there when you need our help. That’s why we’ve put together a team of professional Data Scientists to support you in your journey, meaning you’ll get a response from us within 48 hours maximum.


So, are you ready to embrace the fascinating world of AI?

Come join us, never stop learning, and until then, enjoy AI!

See more

FAQ

FAQ area empty

Course curriculum

25 chương 164 bài học 17 giờ 12 phút 7 bài học thử miễn phí
Chương 1 Welcome to the course!
Chương 2 --- Part 1: Prompt Engineering ---
Chương 3 --- Part 2: Generative AI ---
  • Welcome to Part 2 - Generative AI
  • Fundamentals of Generative AI 3:35
  • Generative AI for Image Generation Học thử 4:12
  • Foundation Models Overview 3:14
  • Foundation Models Lifecycle 3:45
  • Data Selection 3:14
  • Foundation Models Selection 3:33
  • Training vs. Inference 4:47
  • Context Window 1:46
  • Tokens and Embeddings 5:12
  • Transformers 3:37
  • Foundation Models Training 2:08
  • Foundation Models Fine-Tuning 4:02
  • Foundation Model Fine-Tuning [Hands-On] - Short Version 7:59
  • Foundation Model Fine-Tuning [Hands-On] - Long Version
  • Foundation Models Evaluation 3:33
  • Retrieval-Augmented Generation (RAG) 1:43
  • Retrieval Augmented Generation (RAG) [Hands-On] - Short Version 6:42
  • Retrieval Augmented Generation (RAG) [Hands-On] - Long Version
Chương 4 --- Part 3: Agentic AI ---
  • Welcome to Part 3 - Agentic AI
  • AI Agents 1:38
  • Build a Cloud-powered AI Agent for Business Assistance, completely from scratch!
Chương 5 --- Part 4: Fundamentals of Reinforcement Learning ---
  • Welcome to Part 4 - Fundamentals of Reinforcement Learning
Chương 6 Q-Learning Intuition
  • Deep Learning Fundamentals: Neural Networks & Activation Functions Explained 4:03
  • How Reinforcement Learning Works: A Beginner's Guide to AI Training Methods 11:26
  • Bellman Equation in Reinforcement Learning: A Step-by-Step Introduction 18:25
  • From State Values to Optimal Plans: Bellman Equation in AI Decision Making 2:12
  • Markov Decision Processes in Reinforcement Learning: A Complete Guide 16:26
  • RL Tutorial: Optimal Policy vs Fixed Plans in AI Decision Making 12:55
  • Living Penalty in Reinforcement Learning: Optimize AI Agent Decision Making 9:47
  • Q-Learning in Reinforcement Learning: From V-Values to Q-Values Explained 14:45
  • Temporal Difference in Q-Learning: A Complete Guide for Reinforcement Learning 19:26
  • Quiz 1
Chương 7 Q-Learning Implementation
  • A Q-Learning Implementation for Process Optimization
Chương 8 --- Part 5: Deep Q-Learning ---
  • Welcome to Part 5 - Deep Q-Learning
Chương 9 Deep Q-Learning Intuition
  • Deep Learning Fundamentals: Neural Networks & Activation Functions Explained 2:17
  • Deep Q-Learning vs Traditional Q-Learning: Key Differences Explained 15:15
  • How Deep Q-Learning Works: Neural Networks & Reinforcement Learning Explained 6:06
  • Experience Replay in Deep Q-Learning: How it Works & Why it Matters 15:45
  • Q-Learning: Guide to Epsilon-Greedy & Softmax Action Selection Algorithms 16:23
Chương 10 Deep Q-Learning Implementation
  • Get the Codes here
  • Step 1 - Deep Q-Learning Environment Setup: From Gmail to Lunar Lander Training 6:59
  • Google Colab Setup: Deep Q-Learning for Lunar Lander Tutorial 6:24
  • Step 3 - PyTorch DQN Architecture: Building the AI Brain for OpenAI Lunar Lander 8:23
  • PyTorch Deep Q-Learning: Implementing Forward Method for Neural Nets 3:58
  • Step 5 - Configure LunarLander-v2 Environment Parameters for DQN Training 5:45
  • DQN Hyperparameters: Learning Rate & Replay Buffer Setup Guide (Step 6) 3:55
  • Step 7: Implementing Experience Replay Memory in DQN with Python 2:44
  • Step 8: DQN Push Method - Adding Experiences to Replay Memory Buffer 3:07
  • Step 9: Coding DQN Memory Sampling - PyTorch Experience Replay Tutorial 8:17
  • DQN Tutorial: Initialize Q-Networks, Optimizer & Replay Memory Buffer 7:39
  • Step 11: DQN Step Method - Store & Learn from Experiences in Python 7:35
  • Step 12: DQN Action Selection - State Processing to Policy Implementation 8:59
  • Step 13: Deep Q-Network Training - Implementing Learn Method for RL 8:55
  • Step 14 - Deep Q-Network Implementation: Soft Update Method for Stable Training 6:47
  • Step 15: Creating Your First AI Agent - Deep Q-Network (DQN) Tutorial 2:09
  • Step 16 - Epsilon-Greedy Strategy: Initializing AI Training Hyperparameters 5:38
  • Step 17: Deep Q-Learning Training Loop - Complete Lunar Lander Guide 9:39
  • Step 18: DQN Training Visualization - Dynamic Score Tracking Implementation 20:26
  • Step 19: Visualizing Deep Q-Learning - AI Perfects Lunar Lander Landing 5:19
  • ChatGPT vs Custom DQN: Comparing Deep RL Implementations 5:44
Chương 11 --- Part 6: Deep Convolutional Q-Learning ---
  • Welcome to Part 6 - Deep Convolutional Q-Learning
Chương 12 Deep Convolutional Q-Learning Intuition
  • Deep Learning Fundamentals: Neural Networks & Activation Functions Explained 3:26
  • Deep Convolutional Q-Learning: Build AI Agents for Game Environments 7:12
  • Deep Q-Learning vs Eligibility Trace: AI Algorithm Comparison & Guide 8:38
Chương 13 Deep Convolutional Q-Learning Implementation
  • Get the Codes here
  • Deep Q-Learning: Setting Up Pac-Man in OpenAI Gym - Step 1 5:17
  • Step 2 - Implementing DCQN Architecture in Python: Setup & Neural Network Design 5:30
  • Step 3: Building CNNs - Creating AI's Visual Processing System 11:06
  • CNN Architecture: Adding Fully Connected Layers After Convolutional Layers 4:33
  • Step 5: Deep Q-Learning - Building AI's Visual Processing System 7:14
  • Step 6: Configuring Miss Pacman for Deep Q-Learning Training 4:05
  • Step 7: Deep Q-Learning Hyperparameters - Learning Rate & Batch Size Setup 2:03
  • Image Preprocessing for Deep Q-Learning: PIL & Torchvision Implementation 8:20
  • Step 9: Deep Q-Learning to DCQN - Experience Replay & Memory Updates 9:48
  • Step 10: Implementing DCQN Agent - Deep Q-Learning Adaptation & Methods 7:37
  • Step 11: Optimizing DQN Training on V100 GPU - Setup to Solved Environment 14:13
  • Step 12: Visualizing Deep Q-Learning - Watch AI Play Pac-Man Like a Human 3:54
  • Step 13: Deep Q-Learning - Optimizing Neural Networks with GPT-4 5:24
Chương 14 --- Part 7: A3C ---
  • Welcome to Part 7 - A3C
Chương 15 A3C Intuition
  • Deep Learning Fundamentals: Neural Networks & Activation Functions Explained 3:39
  • A3C Algorithm Tutorial: Understanding Asynchronous Advantage Actor-Critic in AI 4:44
  • Actor-Critic Algorithm: From Deep Q-Learning to A3C Implementation 6:36
  • Asynchronous Learning in A3C: Shared Critics and Neural Networks Explained 11:42
  • How Does Advantage Work in Actor-Critic Methods? A3C Algorithm Explained 15:21
  • LSTM in A3C Algorithm: How Memory Enhances Reinforcement Learning Performance 15:36
Chương 16 A3C Implementation
  • Get the Codes here
  • A3C Deep RL: Setting Up Kung Fu Master Environment in Atari 6:06
  • A3C Algorithm Implementation: Neural Network & Environment Setup 5:53
  • Step 3 - A3C Deep Reinforcement Learning: Network Class & Architecture Design 11:46
  • A3C Algorithm: Building Action & State Value Outputs - Step 4 8:26
  • A3C Algorithm: PreprocessAtari Class & Hyperparameter Tuning Setup 5:48
  • Step 6: A3C Agent Class Init Method for Deep Reinforcement Learning 7:14
  • A3C Agent: Converting States to Actions with PyTorch Neural Networks 11:51
  • Step 8: Coding A3C Step Method in PyTorch - Complete Implementation Guide 18:28
  • Step 9 - How to Initialize an A3C Agent in Python: Creating the Agent Instance 2:06
  • Implementing A3C Agent Evaluation in Python | Deep RL Tutorial Step 10 9:59
  • Step 11: EnvBatch Class for A3C Multi-Environment Training in Python 7:22
  • Step 12: Multi-Environment A3C - EnvBatch Class Implementation Tutorial 9:59
  • Step 13: A3C Training - Multi-Environment Batch Setup Implementation 3:46
  • Step 14: A3C Training Loop with Progress Bar for Kung Fu AI Model 20:21
  • ChatGPT A3C Model: PyTorch for KungFuMaster AI Optimization (Step 15) 13:16
Chương 17 --- Part 8: PPO and SAC ---
  • Welcome to Part 8 - PPO and SAC
  • AWS DeepRacer: Training Autonomous Vehicles with PPO and SAC Algorithms 2:06
  • Build and Train the PPO & SAC models for a Self-Driving Car! Theory included.
Chương 18 --- Part 9: Large Language Models (LLMs) ---
  • Welcome to Part 9 - Large Language Models (LLMs)
Chương 19 LLMs Intuition
  • Introduction to Large Language Models (LLMs): Transformers Explained 1:40
  • Building Large Language Models: Essential Ingredients for LLM Development 2:50
  • How Were Large Language Models Invented? Origins of Transformer AI 1:24
  • Understanding Next Word Prediction: How LLMs Process Text One Word at a Time 2:56
  • How Do Large Language Models Work? A Deep Dive into LLM Architecture 4:43
  • What Are LLM Parameters? Understanding Large Language Model Size Explained 2:04
  • Context Windows Explained: How LLMs Remember Conversation History 2:07
  • Fine-Tuning Large Language Models: Real-World Applications and Use Cases 2:58
Chương 20 LLMs Implementation
  • Get the Codes here
  • Fine-Tuning LLMs for Medical Chatbots: A Practical Guide with Hugging Face 2:06
  • Step 1 - Installing & Importing Key Libraries for Fine-Tuning Llama 2 Models 9:59
  • Step 2 - Loading LLaMA 2 Model: Hugging Face Transformers & 4-bit Precision 12:13
  • Step 3 - Loading & Configuring HuggingFace Tokenizer for LLaMA 2 Implementation 7:43
  • Step 4 - Setting Training Arguments for LLM Fine-Tuning in Transformers Library 5:11
  • Step 5 - Implementing SFTTrainer: Memory-Efficient LLM Training with PEFT & LoRA 12:59
  • Step 6: LoRA & Quantization for Efficient LLM Training in Medical Terms 6:42
  • Step 7: Chatting with Your Fine-Tuned Medical LLM via Text Generation 10:37
Chương 21 --- Part 10: Responsible AI ---
  • Welcome to Part 10 - Responsible AI
  • Features of Responsible AI 3:50
  • Guardrails in Generative AI 1:33
  • Amazon Bedrock Guardrails [Hands-On] 6:26
  • Legal Risks of Generative AI 3:15
  • AWS Tools for Responsible AI 2:54
  • Amazon SageMaker Clarify and Monitor [Hands-On] 2:31
  • Amazon Augmented AI [Amazon A2I] [Hands-On] 3:20
  • Interpretability vs. Explainability 4:18
  • SageMaker Model Cards 2:47
  • Amazon SageMaker Model Cards [Hands-On] 5:54
Chương 22 THANK YOU
  • THANK YOU Video 2:40
Chương 23 Annex 1: Artificial Neural Networks
  • What is Deep Learning? A Beginner's Guide to Artificial Neural Networks 12:34
  • Deep Learning Fundamentals: Neural Networks & Activation Functions Explained 2:51
  • How Do Artificial Neurons Work? A Complete Guide to Neural Network Basics 16:15
  • Neural Network Activation Functions: ReLU, Sigmoid, Tanh & Threshold Explained 8:29
  • How Do Neural Networks Work? A Step-by-Step Property Valuation Example 12:47
  • How Do Neural Networks Learn? Understanding Backpropagation & Cost Functions 12:58
  • Understanding Gradient Descent: Optimize Neural Network Weights Efficiently 10:12
  • Stochastic Gradient Descent vs Batch Gradient Descent: What's the Difference? 8:44
  • Backpropagation in Neural Networks: Step-by-Step Training Guide 5:21
Chương 24 Annex 2: Convolutional Neural Networks
  • Deep Learning Fundamentals: Neural Networks & Activation Functions Explained 3:31
  • CNN vs Human Vision: How Convolutional Neural Networks Process Images 15:49
  • CNN Convolution: Feature Detection & Feature Maps in Deep Learning 16:38
  • ReLU in CNN: Understanding Non-Linearity for Deep Learning 6:41
  • Step 2 - Max Pooling in CNN: How to Reduce Feature Maps & Prevent Overfitting 14:13
  • Step 3 - CNN Feature Map Flattening: From Pooling Layer to Neural Network Input 1:52
  • Step 4: CNN Classification - How FC Layers Process Features 19:24
  • CNN Architecture Explained: Feature Detection to Neural Network Classification 4:19
  • Understanding Softmax and Cross-Entropy Loss Functions in Neural Networks 18:20
Chương 25 Congratulations!! Don't forget your Prize :)
  • Bonus Lecture

Requirment

  • High School Maths

  • Basic Python knowledge

Outcomes

  • Understand the theory behind Artificial Intelligence

  • Build 12 different AIs for 12 different applications

  • Master the State of the Art AI models

  • Solve Real World Problems with AI

  • Prompt Engineering

  • Generative AI

  • Image Generation

  • Foundation Models Fine-Tuning

  • Retrieval-Augmented Generation (RAG)

  • Agentic 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)

  • Responsible AI

Instructor

...
Hadelin de Ponteves

0.0

  • ... 0 Student
  • ... 5 Courses
  • ... 0 review

View Details

Reviews

Rate this course :

Remove all