AI with Python Advanced Course

Have you ever wondered how Artificial Intelligence actually works? Do you want to be able to harness the power of neural networks and reinforcement learning to create intelligent agents that can solve tasks with human level complexity?

This is the ultimate course online for learning how to use Python to harness the power of Neural Networks to create Artificially Intelligent agents!

This course focuses on a practical approach that puts you in the driver’s seat to actually build and create intelligent agents, instead of just showing you small toy examples like many other online courses. Here we focus on giving you the power to apply artificial intelligence to your own problems, environments, and situations, not just those included in a niche library!

What you’ll learn

Reinforcement Learning with Python
Creating Artificial Neural Networks with TensorFlow
Using TensorFlow to create Convolution Neural Networks for Images
Using OpenAI to work with built-in game environments
Using OpenAI to create your own environments for any problem
Create Artificially Intelligent Agents
Tabular Q-Learning State–action–reward–state–action (SARSA)
Deep Q-Learning (DQN)
DQN using Convolutional Neural Networks
Cross Entropy Method for Reinforcement Learning
Double DQN
Dueling DQ

Course Content

Module1: Course Overview:

Welcome Message
Course Curriculum Overview
Course Success and Overview

Module2: Set-up & Installation Procedures

Anaconda and Jupyter Notebook Install and Setup
Note on Environment Setup
Environment Setup Walkthrough

Module3: Numpy Basic Over view

Introduction to Numpy Section
NumPy Arrays
Numpy Operations – Part One
Numpy Operations – Part Two
Numpy Exercise Overview
Numpy Exercise Solutions

Module4: Matplotlib & Vistualization Overview

Introduction to Matplotlib
Matplotlib Basics
Matplotlib – Understanding the Figure Object
Matplotlib – Implementing Figures and Axes
Matplotlib – Figure Parameter
Matplotlib – Subplots Functionality19:17
Matplotlib Styling – Legends

Module5: Machine Learning, Deep Learning, & Reinforcement Learning

What is Machine Learning, Deep Learning, and Artificial Intelligence?
Supervised Machine Learning Process

Module6: Pandas and Scikit-Learn Overview

Pandas and Scikit-Learn Overview
Pandas – Series Part One
Pandas – Series Part Two
Pandas – DataFrames – Part One
Pandas – DataFrames – Part Two
Pandas – DataFrames – Part Three
Pandas – DataFrames – Part Four
Scikit-Learn – Using Train-Test-Split
Scikit-Learn – Using Metrics

Module7: Artificial Neural Network & TensorFlow Basics

Perceptron Model
Neural Networks
Activation Functions
Multi-Class Classification Considerations
Cost Functions and Gradient Descent
Backpropagation
TensorFlow vs. Keras Explained
Keras Syntax – Preparing the Data
Keras Syntax – Creating and Training the Model
Keras Syntax – Model Evaluation
Keras Regression – Exploratory Data Analysis
Keras Regression – EDA Continued
Keras Regression – Data Preprocessing and Model Creation
Keras Regression – Model Evaluation and Predictions
Keras Classification – EDA and Preprocessing
Keras Classification – Overfitting and Evaluation
Keras Classification – Overview of Project Options
Keras Project Notebook Exercise Overview
Keras Project Solution – Exploratoy Data Analysis
Keras Project Solutions – Missing Data – Part One
Keras Project Solutions – Dealing with Missing Data – Part Two
Keras Project Solutions – Categorical Data
Keras Project Solutions – Data Preprocessing
Keras Project Solutions- Creating and Training the Model
Keras Project Solutions – Model Evaluation
Tensorboard

Module8: Convolution Neural Networks& Tensor Flow

Convolutional Neural Networks Section Overview
Image Filters and Kernels
Convolutional Layers
Pooling Layers
MNIST Data Set Overview
CNN on MNIST – The Data
CNN on MNIST – Creating and Training the Model
CNN on MNIST – Model Evaluation
CNN on CIFAR-10 – The Data
CNN on CIFAR-10 – Evaluating the Model
Downloading Data Set for Real Image Lectures
CNN on Real Image Files – Reading in the Data
CNN on Real Image Files – Data Generation
CNN on Real Image Files – Creating the Model
CNN on Real Image Files – Model Evaluation
CNN Exercise Project Overview
CNN Exercise Project Solutions

Module9: Reinforcement Learning Core Concepts

Overview of Core Concepts for Reinforcement Learning Section
Agents, Environments, and Policy
Rewards, Discount Factors, and Bellman Equation
Deterministic vs. Stochastic Processes
Tabular Reinforcement Learning

Module 10: OpenAI Overview

Introduction to OpenAI Gym Section
OpenAI Overview and History
OpenAI Gym – Documentation Tour
OpenAI Gym – Environment Key Ideas
OpenAI Gym – Working with the Environment
OpenAI Gym – Agent Interacting with the Environment

Module11: Classical Q-Learning

Introduction to Classical Q-Learning Overview
History of Q-Learning
Q-Learning Theory – Part One – Table Intuition
Q-Learning Theory – Part Two – Q Target Equation
Q-Learning Theory – Part Three – Q-Update Equation
Q-Learning Theory – Part Four – Programmatic Q Updates
Q-Learning Implementation – Part One – Environment Setup
Q-Learning Implementation – Part Two – Table and Hyperparameters
Q-Learning Implementation – Part Three – Update Functions
Q-Learning Implementation – Part Four – Agent Training
Q-Learning Implementation – Part Five – Visualization and Utilization
Continuous Q-Learning Theory – Part One – Environment Setup
Continuous Q-Learning Theory – Part Two- Q-Table Shape
Continuous Q-Learning Theory – Part Three – Discretization Theory
Continuous Q-Learning – Part Four – Discretization Implementation
Continuous Q-Learning – Part Five – Functions and Hyperparameters
Continuous Q-Learning – Part Six – Training and Usage
Q-Learning Exercise Project
Q-Learning Exercise Project – Solutions

Module 12: Deep Q Learning

DQN Section Overview
History of DQN
DQN Theory and Intuition – Part One – Review of Core RL Ideas
DQN Theory and Intuition – Part Two – Neural Networks for RL10:50
DQN Theory and Intuition – Part Three – Feedback and Function Approximation
DQN Theory and Intuition – Part Four – Experience Replay
DQN Theory and Intuition – Part Five – Mapping Key Ideas to Code
DQN Manual Implementation – Part One – Imports and Environment
DQN Manual Implementation – Part Two – Artificial Neural Network
DQN Manual Implementation – Part Three – Hyperparameters and Functions
DQN Manual Implementation – Part Four – Model Training
DQN – Keras-RL2 – Part One – Overview
DQN – Keras-RL2 – Part Two – Imports and Environment
DQN – Keras-RL2 – Part Three – Creating the ANN
DQN – Keras-RL2 – Part Four – DQN Agent
DQN – Exercise Overview
DQN – Exercise Solutions

Module13: Deep Q Learnings on Images

Introduction to Deep Q-Learning on Images
Files for DQN on Images
Key Image Concepts Review
Image History in Replay Buffer – Concept Review
Processing Images Part Three- Coding Replay Buffer and Sequences
Processing Images Part Four – Coding Preprocessing
DQN on Images – Part One – Imports and Processing
DQN on Images – Part Two – Constructing the Network
DQN on Images – Part Three – Setting up the Agent
DQN Exercises Overview
DQN Exercises Solution

Module14: Creating Custom OpenAI Gym Environments

Introduction to Custom OpenAI Gym Environments
Custom Gym Environments – Class Structure Overview
Creating Custom Game – Part One – Snake Game Overview
Creating Custom Game – Part two – Class Structure and Setup
Creating Custom Game – Part Three – Game Reset
Creating Custom Game – Part Four – Direction and Movement
Creating Custom Game – Part Five – Eating and Spawning Food
Creating Custom Game – Part Six – Human Input
Creating Custom Game – Part Seven – Displaying Scor
Creating Custom Game – Part Eight – Game Over Conditions
Creating Custom Game – Part Nine – Ending the Game
Creating Custom Game – Part Ten – Play Logic
Important Note on __init__.py Files
OpenAI Gym Environment – Directory Structure Overview
Gym Directory and Setup File
Filling in the __init__.py Files
Conversion of Game to OpenAI Gym Environment Class
Conversion of Game to OpenAI Gym Environment – Part Two
Registration of the Environment
Training an Agent on the Custom Environment

Who this course is for:

Python developers familiar with basics of machine learning, such as Scikit-Learn, but now want to learn how to create Artificially Intelligent Agents through Reinforcement Learning

International Student Fess: 300 US$

Job Interview Preparation (Soft Skills Questions & Answers)