Topics offered in WSDL 26
(Emphasis on hands-on & real-world applications)

• Basics of Python and Libraries of Importance. 

• Rudiments of Probability Theory for Machine Learning. 

• Basics of Deep Learning Library: PyTorch.

• Essentials of Matrix Calculus and Linear Algebra for Machine Learning.

• Bird’s Eye View of Machine Learning. 

• Primer on Text, Video, and Image Data processing. 

• Gradient-based Optimization techniques.

• Rudiments of Artificial Neural Networks and Backpropagation. 

• Steps towards Deep Learning: Activation, Normalization, Regularization, Loss functions. 

• Convolutional Neural Networks, Architectures of Deep Neural Network Models. 

• Physics Informed Neural Network

• Generative Deep Neural Network Models: GANs, VAEs, and Diffusion. 

• Recurrent Neural Networks and Backpropagation through Time.

• Attention Mechanism and Transformers.

• Introduction to Graph Neural Networks. 

• Introduction to Topological Data Analysis. 

• Explainable and Trustworthy Artificial Intelligence. 

• Emerging Learning strategies: Contrastive learning, Semi-supervised, zero/few-shot, Causal Learning etc.

• Adversarial Attacks, Defence, and Robust Deep Neural Network Models. 

• Deep Reinforcement Learning. 

• Large Language Models, In-Context Learning, Expressiveness of LLMs.

• Agentic AI, Prompt Engineering, RAG.

• LLM Reasoning, Trustworthiness.

• A Day-Long Real-World Project Implementation.

  • Problem Framing and Goal Definition

  • System Architecture and Agent Design

  • Data Acquisition and Environment Setup

  • Implementation and Workflow Orchestration

  • Testing, Evaluation, and Iterative Improvement

  • Deployment, Ethics, and Future Scalability