Introduction to Deep Learning and Neural Networks Backpropagation and Optimization Techniques Activation Functions: ReLU, Sigmoid, Softmax Regularization: Dropout, Batch Normalization

Recurrent Neural Networks (RNNs) – Sequence modeling for time-series data and NLP Convolutional Neural Networks (CNNs) – Image processing and object detection Long Short-Term Memory (LSTM) Networks – Handling long-range dependencies in data

Autoencoders and Variational Autoencoders (VAEs) – Data compression and reconstruction Generative Adversarial Networks (GANs) – Image synthesis and creative AI applications Large Language Models (GPT, BERT, T5) – AI-driven text and content generation Ethical Considerations – Bias, deepfakes, and responsible AI

Real-world applications in Computer Vision, NLP, and Generative AI Deep Learning models for healthcare, finance, robotics, and automation AI-driven recommendation systems and fraud detection

Basics of artificial neural networks (ANNs) Perceptrons and multi-layer perceptrons (MLPs) Feedforward vs. feedback networks Role of weights, biases, and layers

Gradient descent: Batch, Stochastic, and Mini-batch variants Chain rule and computational graphs Optimization algorithms: SGD, Momentum, RMSprop, Adam Learning rate scheduling and adaptive optimization

Wide vs. deep networks Skip connections and residual networks (ResNets) Hyperparameter tuning: Layers, neurons, batch size Early stopping and model checkpointing