HomeCoursesGenerative Systems

Deep Learning A-Z :Neural Networks, AI & ChatGPT Prize

Master deep learning model development in Python with guidance from two seasoned experts in Machine Learning and Data Science. Includes ready-to-use code templates.

Course Material

introduction to Deep Learning (DL)

introduction to Deep Learning (DL) and Applications Get the Codes, Datasets and Slides Here Recommended Workshops before we dive in! Prizes $$ for Learning

Part 1 - Artificial Neural Networks

Welcome to Part 1 - Artificial Neural Networks

ANN Intution

What You'll Need for ANN How Neural Networks Learn: Gradient Descent and Backpropagation Explained Understanding Neurons: The Building Blocks of Artificial Neural Networks Understanding Activation Functions in Neural Networks: Sigmoid, ReLU, and More How Neural Networks works? How Do Neural Networks Learn? Understanding Backpropagation and Cost Functions Mastering Gradient Descent: Key to Efficient Neural Network Training 10:12 How to Use Stochastic Gradient Descent for Deep Learning Optimization Understanding Backpropagation Algorithm: Key to Optimizing Deep Learning Models

Building ANN

Get the code and dataset ready Step 1 - Data Preprocessing for Deep Learning: Preparing Neural Network Dataset Check out our free course on ANN for Regression Step 2 - Data Preprocessing for Neural Networks: Essential Steps and Techniques Step 3 - Constructing an Artificial Neural Network: Adding Input & Hidden Layers Step 4 - Compile and Train Neural Network: Optimizers, Loss Functions & Metrics Step 5 - How to Make Predictions and Evaluate Neural Network Model in Python

Part 2 - Convolutional Neural Networks

Welcome to Part 2 - Convolutional Neural Networks

CNN intuition

What You'll Need for CNN Understanding CNN Architecture: From Convolution to Fully Connected Layers How Do Convolutional Neural Networks Work? Understanding CNN Architecture How to apply convolution filter in Neural Networks? Rectified Linear Units (ReLU) in Deep Learning: Optimizing CNN Performance Understanding Spatial Invariance in CNNs: Max Pooling Explained for Beginners How to Flatten Pooled Feature Maps in Convolutional Neural Networks (CNNs) CNN Building Blocks: Feature Maps, ReLU, Pooling, and Fully Connected Layers Understanding Softmax Activation and Cross-Entropy Loss in Deep Learning

Building CNN

Get the code and dataset ready Step 1 - Convolutional Neural Networks Explained: Image Classification Tutorial Step 2 - Deep Learning Preprocessing: Scaling & Transforming Images for CNNs Step 3 - Building CNN Architecture: Convolutional Layers & Max Pooling Explained Step 4 - Train CNN for Image Classification: Optimize with Keras & TensorFlow Step 5 - Deploying a CNN for Real-World Image Recognition Develop an Image Recognition System Using Convolutional Neural Networks

Part 3 - Recurrent Neural Networks

Welcome to Part 3 - Recurrent Neural Networks

RNN Intuition

What You'll Need for RNN How Do Recurrent Neural Networks (RNNs) Work? Deep Learning Explained What is a Recurrent Neural Network (RNN)? Deep Learning for Sequential Data Understanding the Vanishing Gradient Problem in Recurrent Neural Networks (RNNs) Understanding Long Short-Term Memory (LSTM) Architecture for Deep Learning How LSTMs Work in Practice: Visualizing Neural Network Predictions LSTM Variations: Peepholes, Combined Gates, and GRUs in Deep Learning

Building RNN

Get the code and dataset ready Step 1 - Building a Robust LSTM Neural Network for Stock Price Trend Prediction Step 2 - Importing Training Data for LSTM Stock Price Prediction Model Step 3 - Applying Min-Max Normalization for Time Series Data in Neural Networks Step 4 - Building X_train and y_train Arrays for LSTM Time Series Forecasting Step 5 - Preparing Time Series Data for LSTM Neural Network in Stock Forecasting Step 6 - Create RNN Architecture: Sequential Layers vs Computational Graphs Step 7 - Adding First LSTM Layer: Key Components for Stock Market Prediction Step 8 - Implementing Dropout Regularization in LSTM Networks for Forecasting Step 9 - Finalizing RNN Architecture: Dense Layer for Stock Price Forecasting Step 10 - Compile RNN with Adam Optimizer for Stock Price Prediction in Python Step 11 - Optimizing Epochs and Batch Size for LSTM Stock Price Forecasting Step 12 - Visualizing LSTM Predictions: Real vs Forecasted Google Stock Prices Step 13 - Preparing Historical Stock Data for LSTM Model: Scaling and Reshaping Step 14 - Creating 3D Input Structure for LSTM Stock Price Prediction in Python Step 15 - Visualizing LSTM Predictions: Plotting Real vs Predicted Stock Prices

Evaluating the RNN

Evaluating the RNN Improving the RNN

Part 4 - Self Organizing Maps

Welcome to Part 4 - Self Organizing Maps

SOM Intuition

How Do Self-Organizing Maps Work? Understanding SOM in Deep Learning Self-Organizing Maps (SOM): Unsupervised Deep Learning for Dimensionality Reduct Why K-Means Clustering is Essential for Understanding Self-Organizing Maps Self-Organizing Maps Tutorial: Dimensionality Reduction in Machine Learning How Self-Organizing Maps (SOMs) Learn: Unsupervised Deep Learning Explained Interpreting SOM Clusters: Unsupervised Learning Techniques for Data Analysis Understanding K-Means Clustering: Intuitive Explanation with Visual Examples K-Means Clustering: Avoiding the Random Initialization Trap in Machine Learning How to Find the Optimal Number of Clusters in K-Means: WCSS and Elbow Method

Building SOM

Get the code and dataset ready Step 1 - Implementing Self-Organizing Maps (SOMs) for Fraud Detection in Python Step 2 - SOM Weight Initialization and Training: Tutorial for Anomaly Detection Step 3 - SOM Visualization Techniques: Colorbar & Markers for Outlier Detection Step 4 - Catching Cheaters with SOMs: Mapping Winning Nodes to Customer Data

Mega Case Study

Get the code and dataset ready Step 1 - Building a Hybrid Deep Learning Model for Credit Card Fraud Detection Step 2 - Developing a Fraud Detection System Using Self-Organizing Maps Step 3 - Building a Hybrid Model: From Unsupervised to Supervised Deep Learning Step 4 - Implementing Fraud Detection with SOM: A Deep Learning Approach

Part 5 - Boltzmann Machines

Welcome to Part 5 - Boltzmann Machines

Boltzmann Machines: intuition

Understanding Boltzmann Machines: Deep Learning Fundamentals for AI Enthusiasts Boltzmann Machines vs. Neural Networks: Key Differences in Deep Learning Deep Learning Fundamentals: Energy-Based Models & Their Role in Neural Networks How to Edit Wikipedia: Adding Boltzmann Distribution in Deep Learning Restricted Boltzmann Machines How Energy-Based Models Work: Deep Dive into Contrastive Divergence Algorithm Deep Belief Networks: Understanding RBM Stacking in Deep Learning Models Deep Boltzmann Machines vs Deep Belief Networks: Key Differences Explained

Buiiding Boltzmann Machines:

Get the code and dataset read Step 0 - Building a Movie Recommender System with RBMs: Data Preprocessing Guide Same Data Preprocessing in Parts 5 and 6 Step 1 - Importing Movie Datasets for RBM-Based Recommender Systems in Python Step 2 - Preparing Training and Test Sets for Restricted Boltzmann Machine Step 3 - Preparing Data for RBM: Calculating Total Users and Movies in Python Step 4 - Convert Training & Test Sets to RBM-Ready Arrays in Python Step 5 - Converting NumPy Arrays to PyTorch Tensors for Deep Learning Models Step 6 - RBM Data Preprocessing: Transforming Movie Ratings for Neural Networks Step 7 - Implementing Restricted Boltzmann Machine Class Structure in PyTorch Step 8 - RBM Hidden Layer Sampling: Bernoulli Distribution in PyTorch Tutorial Step 9 - RBM Visible Node Sampling: Bernoulli Distribution in Deep Learning Step 10 - RBM Training Function: Updating Weights and Biases with Gibbs Sampling Step 11 - How to Set Up an RBM Model: Choosing NV, NH, and Batch Size Parameters Step 12 - RBM Training Loop: Epoch Setu and Loss Function Implementation Step 13 - RBM Training: Updating Weights and Biases with Contrastive Divergence Step 14 - Optimizing RBM Models: From Training to Test Set Performance Analysis Evaluating the Boltzmann Machine

Part 6 - AutoEncoders

Welcome to Part 6 - AutoEncoders

AutoEncoders intuition

Deep Learning Autoencoders: Types, Architecture, and Training Explained Autoencoder Bias in Deep Learning: Improving Neural Network Performance How to Train an Autoencoder: Step-by-Step Guide for Deep Learning Beginners How to Use Overcomplete Hidden Layers in Autoencoders for Feature Extraction Sparse Autoencoders in Deep Learning: Preventing Overfitting in Neural Networks Denoising Autoencoders: Deep Learning Regularization Technique Explained What are Contractive Autoencoders? Deep Learning Regularization Techniques What are Stacked Autoencoders in Deep Learning? Architecture and Applications Deep Autoencoders vs Stacked Autoencoders: Key Differences in Neural Networks

Building AutoEncoders

Get the code and dataset ready Same Data Preprocessing in Parts 5 and 6 Step 1 - Building a Movie Recommendation System with AutoEncoders: Data Import Step 2 - Preparing Training and Test Sets for Autoencoder Recommendation System Step 3 - Preparing Data for Recommendation Systems: User & Movie Count in Python Homework Challenge - Coding Exercise Step 4 - Prepare Data for Autoencoder: Creating User-Movie Rating Matrices Step 5 - Convert Training and Test Sets to PyTorch Tensors for Deep Learning Step 6 - Building Autoencoder Architecture: Class Creation for Neural Networks Step 7 - Python Autoencoder Tutorial: Implementing Activation Functions & Layers Step 8 - PyTorch Techniques for Efficient Autoencoder Training on Large Datasets Step 9 - Implementing Stochastic Gradient Descent in Autoencoder Architecture Step 10 - Machine Learning Metrics: Interpreting Loss in Autoencoder Training Step 11 - How to Evaluate Recommender System Performance Using Test Set Loss

Annex - Get the Machine Learning Basics

Regression & Classification

hat You Need for Regression & Classification Simple Linear Regression: Understanding Y = B0 + B1X in Machine Learning Linear Regression Explained: Finding the Best Fitting Line for Data Analysis Multiple Linear Regression - Understanding Dependent & Independent Variables Understanding Logistic Regression: Intuition and Probability in Classification

Data Preprocessing

Data Preprocessing How to Scale Features in Machine Learning: Normalization vs Standardization Machine Learning Basics: Using Train-Test Split to Evaluate Model Performance Machine Learning Workflow: Data Splitting, Feature Scaling, and Model Training

Data Preprocessing in Python

Step 1 - Data Preprocessing in Python: Essential Tools for ML Models Step 2 - How to Handle Missing Data in Python: Data Preprocessing Techniques Step 1 - Importing Essential Python Libraries for Data Preprocessing & Analysis Step 1 - Creating a DataFrame from CSV: Python Data Preprocessing Basics Step 2 - Pandas DataFrame Indexing: Building Feature Matrix X with iloc Method Step 3 - Preprocessing Data: Extracting Features and Target Variables in Python For Python learners, summary of Object-oriented programming: classes & objects Step 1 - Handling Missing Data in Python: SimpleImputer for Data Preprocessing Step 2 - Preprocessing Datasets: Fit and Transform to Handle Missing Values Step 1 - Preprocessing Categorical Variables: One-Hot Encoding in Python Step 2 - Using fit_transform Method for Efficient Data Preprocessing in Python 05:54 Step 3 - Preprocessing Categorical Data: One-Hot and Label Encoding Techniques Step 1 - Machine Learning Data Prep: Splitting Dataset Before Feature Scaling Step 2 - Split Data into Train & Test Sets with Scikit-learn's train_test_split Step 3 - Preparing Data for ML: Splitting Datasets with Python and Scikit-learn Step 1 - How to Apply Feature Scaling for Preprocessing Machine Learning Data Step 2 - Feature Scaling in Machine Learning: When to Apply StandardScaler Step 3 - Normalizing Data with Fit and Transform Methods in Scikit-learn Step 4 - How to Apply Feature Scaling to Training & Test Sets in ML

Logistic Regression

Understanding the Logistic Regression Equation: A Step-by-Step Guide How to Calculate Maximum Likelihood in Logistic Regression: Step-by-Step Guide Step 1a - Machine Learning Classification: Logistic Regression in Python Step 1b - Logistic Regression Analysis: Importing Libraries and Splitting Data Step 2a - Data Preprocessing for Logistic Regression: Importing and Splitting Step 2b - Data Preprocessing: Feature Scaling for Machine Learning in Python Step 3a - Implementing Logistic Regression for Classification with Scikit-Learn Step 3b - Predicting Purchase Decisions with Logistic Regression in Python Step 4a - Using Classifier Objects to Make Predictions in Machine Learning Step 4b - Evaluating Logistic Regression Model: Predicted vs Real Outcomes Step 5 - Evaluating Machine Learning Models: Confusion Matrix and Accuracy Step 6a - Creating a Confusion Matrix for Machine Learning Model Evaluation Step 6b - Visualizing Machine Learning Results: Training vs Test Set Comparison Step 7a - Visualizing Logistic Regression: 2D Plots for Classification Models Step 7b - Visualizing Logistic Regression: Interpreting Classification Results Step 7c - Visualizing Test Results: Assessing Machine Learning Model Accuracy Logistic Regression in Python - Step 7 (Colour-blind friendly image) Machine Learning Regression and Classification EXTRA EXTRA CONTENT: Logistic Regression Practical Case Study

Description

As seen on Kickstarter. Powered by Aiwebsoul.

Artificial Intelligence is advancing faster than ever. From self-driving cars to AI-powered medical diagnostics and intelligent recommendation engines, we are witnessing a technological revolution. At the heart of this transformation is Deep Learning — the engine that enables machines to solve complex, human-level problems. That’s why we created Deep Learning A-Z at Aiwebsoul: a cutting-edge training experience that gives you the skills, intuition, and tools to thrive in the age of AI.

What makes this course different is not just the content — it’s how we teach it. Deep Learning is a complex field, but we’ve designed this course to give you a clear and intuitive understanding from the ground up. It’s structured around two main branches of Deep Learning: Supervised and Unsupervised learning. Each is broken into focused, algorithm-driven modules that help you build mastery step by step. We don’t just throw code and math at you — we start each topic with intuition tutorials that explain the why behind every method, so you truly understand what’s happening under the hood before jumping into the code.

This isn’t your typical course filled with outdated datasets and toy problems. Inside Deep Learning A-Z, you’ll work on real-world challenges that data scientists face every day. You’ll build an Artificial Neural Network to reduce customer churn for a bank, train a CNN to distinguish between cats and dogs (and reapply it to medical image classification), use LSTMs to forecast Google’s stock price, build a fraud detection system with Self-Organizing Maps, and develop two powerful recommender systems using Boltzmann Machines and Autoencoders — one of which tackles a challenge inspired by the Netflix $1 million prize.

And here’s the best part — it’s all hands-on. Every coding exercise starts from a blank page. We build the models together from scratch in Python using TensorFlow, PyTorch, Keras, Theano, and Scikit-learn. We show you not just how to write the code, but how to structure it so you can adapt it to your own datasets and business challenges. You’ll also learn the supporting tools of the trade — NumPy, Pandas, and Matplotlib — so you’ll have everything you need to launch real AI projects on your own.

What truly sets Deep Learning A-Z apart is our commitment to your success. Whether you’re a student, developer, business owner, or aspiring data scientist, you’ll have full support from our team of professional AI instructors. We respond to every question within 48 hours, ensuring you’re never stuck or left behind.

So, whether you’re just starting out or looking to deepen your existing knowledge, this course will empower you to think, build, and deploy like a real AI engineer. Join thousands of learners around the world who are gaining real Deep Learning skills — not just for resumes, but for building the future.

Welcome to Deep Learning A-Z by Aiwebsoul — where code meets intuition, and ideas become innovation.