π Chapter 1: Introduction to Deep Learning
- What is Deep Learning?
- Difference between Machine Learning and Deep Learning
- Applications of Deep Learning
- History and Evolution
π Chapter 2: Mathematical Foundations
- Linear Algebra Basics (Matrix, Vectors, Tensors)
- Calculus (Derivatives, Gradients)
- Probability and Statistics
- Chain Rule and Partial Derivatives
π Chapter 3: Neural Networks Basics
- Biological Neuron vs Artificial Neuron
- Perceptron and Multi-layer Perceptron (MLP)
- Activation Functions (Sigmoid, Tanh, ReLU)
- Loss Functions and Optimization
π Chapter 4: Backpropagation and Training
- Forward Pass and Loss Calculation
- Backward Pass (Gradient Descent)
- Learning Rate, Epochs, Batches
- Overfitting, Underfitting and Regularization
π Chapter 5: Deep Neural Networks (DNN)
- Architecture of DNN
- Vanishing/Exploding Gradients
- Weight Initialization Techniques
- Batch Normalization
π Chapter 6: Convolutional Neural Networks (CNNs)
- What is Convolution?
- CNN Layers (Convolution, Pooling, Flatten, Dense)
- Use in Image Classification
- Famous CNN Architectures (LeNet, AlexNet, VGG, ResNet)
π Chapter 7: Recurrent Neural Networks (RNNs)
- Introduction of RNN
- Sequence Data and Time-Series
- RNN Structure
- Vanishing Gradient Problem in RNNs
- LSTM and GRU Networks
π Chapter 8: Transfer Learning & Pretrained Models
- What is Transfer Learning?
- Feature Extraction vs Fine Tuning
- Pretrained Models (VGG, ResNet, Inception, BERT)
π Chapter 9: Autoencoders & Representation Learning
- What is an Autoencoder?
- Encoder-Decoder Structure
- Variational Autoencoders (VAE)
- Applications: Denoising, Dimensionality Reduction
π Chapter 10: Generative Adversarial Networks (GANs)
π Chapter 11: Deep Reinforcement Learning
π Chapter 12: Natural Language Processing with Deep Learning
- Introduction of NLP
- Word Embeddings (Word2Vec, GloVe)
- Sequence Models for Text (RNN, LSTM)
- Transformers and BERT
π Chapter 13: Frameworks and Tools
- TensorFlow and Keras Basics
- PyTorch Basics
- Model Training, Saving, and Loading in PyTroch
- Model Training, Saving, and Loading in Keras
- Using GPUs/TPUs
π Chapter 14: Model Evaluation and Deployment
- what is Model Evaluation and Deployment
- Evaluation Metrics ,Confusion Matrix, Precision, Recall
- Saving & Exporting Models
- Serving via API / Web App