Deep Learning A-Z 2024: Neural Networks, AI & ChatGPT Bonus

Learn to create Deep Learning Algorithms in Python from two Machine Learning & Data Science experts. Master Neural Networks, AI, and leverage ChatGPT for cutting-edge applications.

4.5 (183,396 ratings) | 200,000 students

Created by Kirill Eremenko, Hadelin de Ponteves, Ligency Team

Bestseller Updated May 2025 | 26 hours total | English

Deep Learning A-Z 2024: Neural Networks, AI & ChatGPT Bonus

By Kirill Eremenko, Hadelin de Ponteves, Ligency Team

4.5 (183,396)

₹549 ₹649

Discount applied with code: ST21MT30625G1

30-Day Money-Back Guarantee

This course includes:

26 hours on-demand video
40 articles
50 downloadable resources
Access on mobile and TV
Certificate of completion

What You'll Learn

Understand the intuition behind Artificial Neural Networks (ANNs).
Master Convolutional Neural Networks (CNNs) for image processing.
Apply Recurrent Neural Networks (RNNs) for time-series data.
Implement Self-Organizing Maps (SOMs) for clustering.
Use Boltzmann Machines and AutoEncoders for advanced applications.
Leverage Generative AI and ChatGPT for cutting-edge projects.
Make powerful predictions using deep learning models.
Apply deep learning to real-world problems like fraud detection and image recognition.
Use TensorFlow, Keras, and PyTorch effectively.

Course Content

10 sections • 120 lectures • 26h total length

Welcome to the Course 10min
What is Deep Learning? 12min
Setting Up Python and Libraries 10min
Introduction to Neural Networks 10min
Key Concepts in AI 10min
Overview of Course Projects 5min
Resources and Community 3min
Quiz: Deep Learning Basics 2min

Intuition Behind ANNs 15min
Building an ANN in Python 20min
Activation Functions 15min
Gradient Descent and Backpropagation 20min
Optimizing ANN Performance 15min
Hyperparameter Tuning 15min
Coding Challenge: ANN for Regression 20min
Project: Customer Churn Prediction 30min
Quiz: ANNs 8min
Debugging ANN Models 12min
Code Review: ANNs 10min
Real-World Applications 10min

Intuition Behind CNNs 15min
Convolutional Layers 20min
Pooling and Fully Connected Layers 15min
Building a CNN in Keras 20min
Data Augmentation 15min
Transfer Learning 15min
Coding Challenge: Image Classification 20min
Project: Cat vs. Dog Classifier 30min
Quiz: CNNs 8min
Debugging CNN Models 12min
Code Review: CNNs 10min
Applications in Computer Vision 10min

Intuition Behind RNNs 15min
LSTMs and GRUs 20min
Building an RNN in PyTorch 18min
Handling Sequential Data 15min
Time-Series Prediction 15min
Coding Challenge: Stock Price Prediction 20min
Project: Stock Price Forecaster 25min
Quiz: RNNs 8min
Debugging RNN Models 12min
Code Review: RNNs 10min

Intuition Behind SOMs 15min
Implementing SOMs in Python 20min
Clustering with SOMs 15min
Visualizing SOM Results 15min
Applications of SOMs 15min
Coding Challenge: Customer Segmentation 20min
Project: Market Segmentation with SOMs 25min
Quiz: SOMs 8min
Debugging SOM Models 12min
Code Review: SOMs 10min

Intuition Behind Boltzmann Machines 15min
Restricted Boltzmann Machines (RBMs) 20min
Implementing RBMs in Python 18min
Energy-Based Models 15min
Training Boltzmann Machines 15min
Coding Challenge: Recommendation System 20min
Project: Movie Recommendation System 25min
Quiz: Boltzmann Machines 8min
Debugging RBM Models 12min
Code Review: Boltzmann Machines 10min

Intuition Behind AutoEncoders 15min
Building AutoEncoders in TensorFlow 20min
Variational AutoEncoders (VAEs) 15min
Denoising AutoEncoders 15min
Applications of AutoEncoders 15min
Coding Challenge: Image Denoising 20min
Project: Image Reconstruction with AutoEncoders 25min
Quiz: AutoEncoders 8min
Debugging AutoEncoder Models 12min
Code Review: AutoEncoders 10min

Introduction to Generative AI 15min
Understanding ChatGPT 20min
Integrating ChatGPT in Projects 15min
Generative Adversarial Networks (GANs) 15min
Building a Simple GAN 15min
Coding Challenge: Text Generation 20min
Project: AI-Powered Chatbot 25min
Quiz: Generative AI 8min
Debugging GAN Models 12min
Code Review: Generative AI 10min

Introduction to Model Deployment 15min
Deploying Models with Flask 20min
Using Cloud Platforms (AWS, GCP) 15min
Model Optimization for Production 15min
Monitoring Deployed Models 15min
Coding Challenge: Deploy a CNN 20min
Project: Fraud Detection API 25min
Quiz: Model Deployment 8min
Debugging Deployment Issues 12min
Code Review: Deployment 10min

Project Overview and Planning 15min
Data Collection and Preprocessing 20min
Building a Hybrid Model (CNN+RNN) 25min
Integrating ChatGPT Features 20min
Model Training and Evaluation 15min
Deploying the Model 20min
Testing and Optimization 15min
Project: AI-Powered Image Captioning 30min
Quiz: Capstone Concepts 8min
Code Review: Capstone Project 10min

Requirements

High school mathematics knowledge (basic algebra).
Basic Python programming knowledge.
No prior deep learning experience required.
A computer with internet access and Python installed.

Description

Learn to create Deep Learning Algorithms in Python from two Machine Learning & Data Science experts. This comprehensive course covers Artificial Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Self-Organizing Maps, Boltzmann Machines, AutoEncoders, and Generative AI. With hands-on templates and practical projects, you'll apply deep learning to real-world problems like fraud detection, image recognition, stock price prediction, and customer segmentation.

Updated for 2024, this course includes a special ChatGPT bonus section to leverage generative AI for cutting-edge applications. Whether you're a beginner or an experienced programmer, you'll gain the skills to build powerful deep learning models using TensorFlow, Keras, and PyTorch. No advanced math or prior AI experience is required—just basic Python and high school math. Join over 200,000 students and start your journey to mastering Deep Learning today!

This course provides downloadable templates, datasets, and step-by-step guidance to ensure you can apply what you learn to your own data. By the end, you'll be equipped to tackle real-world AI challenges and take advantage of the latest advancements in generative AI, including ChatGPT integration.

Instructors

Kirill Eremenko

Data Science & Machine Learning Expert

2,200,000 students | 20+ courses

Kirill Eremenko is a Data Science expert with a passion for teaching practical applications of AI and machine learning. With over 2.2M students on Udemy, his courses focus on real-world problem-solving.

Hadelin de Ponteves

AI & Machine Learning Specialist

1,000,000 students | 10+ courses

Hadelin de Ponteves is an AI enthusiast who simplifies complex machine learning concepts. His engaging teaching style has helped over 1M students master AI and deep learning.

Ligency Team

Course Support & Content Creators

500,000 students | 5+ courses

The Ligency Team supports course updates, ensuring content is fresh and relevant. They specialize in delivering high-quality AI and data science education.

Student Reviews

5.0

"The explanations are clear, and the practical projects make it easy to apply the concepts. The ChatGPT section is a game-changer!" – Anonymous Student

4.5

"Great course for beginners and intermediates. The hands-on projects are fantastic, and the instructors break down complex topics well." – Sarah T.