Fourth Winter School on Deep Learning (WSDL) Reinforcing Science with Foundation Models: Towards an Amazing Confluence

• Sanghamitra Bandyopadhyay
• Bhabatosh Chanda
• Dipti Prasad Mukherjee
• Naqueeb Ahmad Warsi
• Pinakpani Pal
• Sumana Ghosh
• Utpal Garain

Organizing Chairs

• Aditya Panda
• Anish Chakrabarty
• Faizanuddin Ansari
• Kushal Bose
• Susmita Ghosh
• Priyobrata Mondal

Administrative Chairs

• Arghya Pratihar
• Bhaskar Pramanik

•  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 of Error.
•  Tree-based Classifiers and Ensemble Techniques.
•  Steps towards Deep Learning: Activation, Normalization, Regularization, Loss functions.
•  Convolutional Neural Networks, Architectures of Deep Neural Network Models.
•  Generative Deep Neural Network Models: GANs, VAEs, and Diffusion.
•  Recurrent Neural Networks and Backpropagation through Time.
•  Attention Mechanism and Transformers: Where Text meets Vision.
•  Introduction to Graph Neural Networks.
•  Introduction to Topological Data Analysis.
•  Explainable and Trustworthy Artificial Intelligence.
•  Emerging Learning strategies: Contrastive learning, Semi-supervised, few-shot, zero-shot, etc.
•  Adversarial Attacks, Defence, and Robust Deep Neural Network Models.
•  Theory of Deep Learning Special Focus on GenAI.
•  Deep Reinforcement Learning.
•  Large Language Models, prompt engineering, RAG, expressiveness of LLMs and fine-tuning. 
•  Introduction to Deep Learning-based Speech Synthesis.
• Physics Neformed Neural Networks
• Neural Algorithmic Learning