Deep Learning

Overview

This course provides a comprehensive introduction to deep learning through hands-on implementation using Python, NumPy, Pandas, TensorFlow, and Keras. It begins with foundational concepts and gradually progresses to advanced architectures such as CNNs, RNNs, LSTMs, and transformers. Learners will gain practical experience in data preprocessing, model design, training, optimization, and deployment. The curriculum emphasizes real-world applications across computer vision, natural language processing, and generative AI.

Objectives

• Understand the fundamentals of neural networks and implement basic artificial neural networks using TensorFlow and Keras.
• Apply deep learning techniques to solve real-world problems including image classification, time series forecasting, and text processing.

Key topics

• Introduction to Deep Learning and its Applications
• Convolutional Neural Networks for Image Classification
• Recurrent Neural Networks for Sequential Data
• Natural Language Processing with Word Embeddings

Expected outcomes

• Build and train convolutional neural networks for image recognition tasks such as handwritten digit classification and object detection.
• Develop recurrent neural networks for sequence prediction and natural language understanding, including sentiment analysis and text generation.

How the AI Tutor can help

How the Skillama AI Tutor helps with the listed lectures: explanations, follow-up questions, and running or debugging practice code.

Who this is for

This course is designed for learners seeking to build practical skills in deep learning using Python and frameworks like TensorFlow and Keras.

Curriculum

1. 1. Introduction to Deep Learning

   • Introduction to Artificial Intelligence, Machine Learning & Deep Learning
   • Evolution of Deep Learning
   • Applications of Deep Learning
   • Deep Learning vs Machine Learning
   • Deep Learning Workflow
   • Industry Use Cases
   • Hands-on: Setting up Python Environment
   • Hands-on: Installing TensorFlow & Keras
   • Hands-on: Running Your First Deep Learning Model

2. 2. Python & Mathematical Foundations

   • NumPy for Deep Learning
   • Pandas Basics
   • Matrix Operations
   • Linear Algebra Fundamentals
   • Probability & Statistics
   • Calculus Concepts
   • Gradient Descent Basics
   • Hands-on: Matrix Operations
   • Hands-on: Data Preprocessing using NumPy & Pandas

3. 3. Neural Networks Fundamentals

   • Biological vs Artificial Neurons
   • Perceptron
   • Artificial Neural Networks (ANN)
   • Layers in Neural Networks
   • Activation Functions
   • Feed Forward Networks
   • Loss Functions
   • Backpropagation
   • Hands-on: Build First ANN using TensorFlow/Keras

4. 4. TensorFlow & Keras

   • TensorFlow Architecture
   • Tensor Operations
   • Keras API
   • Sequential API
   • Functional API
   • Model Compilation
   • Training & Evaluation
   • Saving & Loading Models
   • Hands-on: Customer Churn Prediction Model

5. 5. Data Preprocessing

   • Data Cleaning
   • Feature Scaling
   • Label Encoding
   • One-Hot Encoding
   • Handling Missing Values
   • Train-Test Split
   • Data Augmentation
   • Hands-on: Prepare Dataset for Deep Learning

6. 6. Artificial Neural Networks (ANN)

   • Designing ANN Models
   • Hidden Layers
   • Optimizers
   • Learning Rate
   • Batch Size
   • Epochs
   • Model Evaluation
   • Regularization
   • Hands-on: Bank Customer Churn Prediction
   • Hands-on: Employee Attrition Prediction

7. 7. Convolutional Neural Networks (CNN)

   • Introduction to CNN
   • Image Processing Basics
   • Convolution Layer
   • Pooling Layer
   • Flatten Layer
   • Fully Connected Layer
   • Transfer Learning
   • Image Classification
   • Hands-on: Handwritten Digit Recognition (MNIST)
   • Hands-on: Cat vs Dog Image Classifier

8. 8. Recurrent Neural Networks (RNN)

   • Sequential Data
   • RNN Architecture
   • Vanishing Gradient Problem
   • Time Series Forecasting
   • Text Processing
   • Hands-on: Stock Price Prediction
   • Hands-on: Weather Forecasting

9. 9. LSTM & GRU Networks

   • Long Short-Term Memory (LSTM)
   • Gated Recurrent Unit (GRU)
   • Sequence Prediction
   • Text Generation
   • Sentiment Analysis
   • Hands-on: Movie Review Sentiment Analysis
   • Hands-on: Text Prediction Model

10. 10. Natural Language Processing with Deep Learning

    • Text Preprocessing
    • Tokenization
    • Word Embeddings
    • Word2Vec
    • GloVe
    • Attention Mechanism
    • Transformer Basics
    • BERT Introduction
    • Hands-on: Spam Email Detection
    • Hands-on: News Classification

11. 11. Computer Vision

    • OpenCV Basics
    • Image Processing
    • Face Detection
    • YOLO Overview
    • Image Segmentation
    • Hands-on: Face Mask Detection
    • Hands-on: Object Detection Demo

12. 12. Transfer Learning

    • Pre-trained Models
    • VGG16
    • ResNet
    • Inception
    • MobileNet
    • Fine-Tuning Models
    • Hands-on: Flower Image Classification
    • Hands-on: Custom Image Classifier

13. 13. Model Optimization

    • Dropout
    • Batch Normalization
    • Early Stopping
    • Hyperparameter Tuning
    • Model Checkpoint
    • TensorBoard
    • Hands-on: Optimize CNN Performance

14. 14. Model Deployment

    • Saving Models
    • TensorFlow Serving
    • Flask API
    • FastAPI Basics
    • Streamlit Deployment
    • Docker Overview
    • Cloud Deployment (AWS/GCP/Azure)
    • Hands-on: Deploy Image Classification API

15. 15. Generative AI Fundamentals

    • Introduction to Generative AI
    • Autoencoders
    • GANs (Introduction)
    • Diffusion Models Overview
    • Large Language Models (LLMs)
    • Prompt Engineering Basics
    • Hands-on: Image Generation Demo

16. 16. Mini Project

    • Plant Disease Detection System
    • Leaf Image Collection
    • Image Preprocessing
    • CNN Model Training
    • Disease Classification
    • Accuracy Evaluation
    • Prediction Reports