Course Content
Section outline
-
Session 1: Introduction to Deep Learning (1 Hour)
- AI vs. Machine Learning vs. Deep Learning
- Deep Learning Applications:
- Computer Vision (Image classification, object detection)
- Natural Language Processing (NLP) (Sentiment analysis, machine translation)
- Speech Recognition
- Basic Neural Network Architecture
Session 2: Neural Networks (2 Hours)
- Perceptron & Multi-Layer Perceptron (MLP)
- Gradient Descent & Backpropagation
- Optimization Techniques: SGD, Adam
- Activation Functions: Sigmoid, ReLU, Tanh
- Loss Functions: MSE, Cross-Entropy
Hands-on Lab: Training a Neural Network using TensorFlow/Keras
Session 3: Deep Learning Frameworks (1 Hour)
- Installing & Setting Up TensorFlow/Keras
- Building a Simple Neural Network with Keras
Hands-on Lab: Train a Neural Network on the MNIST Dataset
Session 4: Convolutional Neural Networks (CNNs) (3 Hours)
- Convolutional Layers, Pooling & Feature Extraction
- CNN Applications: Image Classification, Object Detection
Hands-on Lab: Train a CNN on the CIFAR-10 Dataset
-
Session 5: Recurrent Neural Networks (RNNs) (2 Hours)
- Introduction to RNNs, LSTMs, and GRUs
- Time-Series Forecasting & Text Generation
Hands-on Lab: Train an LSTM for Sentiment Analysis
Session 6: Transfer Learning & Fine-Tuning (2 Hours)
- What is Transfer Learning?
- Using Pre-Trained Models (VGG16, ResNet, Inception)
Hands-on Lab: Fine-Tune a Pre-Trained Model for Custom Image Classification
Session 7: Generative Models (2 Hours)
- Introduction to GANs (Generative Adversarial Networks)
- Generator vs. Discriminator Architecture
Hands-on Lab: Train a GAN for Image Generation
Session 8: Model Deployment & AI in Production (1 Hour)
- Model Optimization & Evaluation (Accuracy, Precision, Recall, F1 Score, ROC)
- Deploying Models using Flask & TensorFlow Serving
Hands-on Lab: Serve a Deep Learning Model via a REST API
