Calendar

Applying statistical and visual techniques to explore datasets and generate hypotheses.

This session walks through a full ML workflow—from using pretrained models to training with labeled data—using tools like Data-to-Science, Jupyter, PyTorch, GitHub, and Huggingface.

This session focuses on Recurrent Neural Networks (RNNs) for sequential data, explaining their use of hidden states for memory, the training challenges they face, and how advanced variants like LSTMs and GRUs use gating mechanisms to overcome these issues.

Understanding fundamental AI and ML concepts, terminology, and the machine learning workflow.

A session designed to enhance team communication and ensure research objectives are clearly defined and effectively communicated through structured planning processes.

Introduction to the revolutionary "Attention is All You Need" concept. Will focus on how attention allows models to weigh the importance of different parts of the input sequence, overcoming limitations of RNNs.

Implementing basic supervised and unsupervised learning models using Scikit-learn.

This session explores how LLMs interact with external tools and APIs through function calling, including defining and using tools, processing outputs, integrating capabilities like calculators and web search, and generating SQL from natural language using techniques like RAG and multi-dialect handling, with practical database exercises.

This session delves into Convolutional Neural Networks (CNNs) for image processing, covering key components like convolutional and pooling layers, fully connected layers, and core concepts such as parameter sharing, receptive fields, and hierarchical feature learning, with brief reference to notable CNN architectures.

Introduction to text data processing, feature extraction, and simple NLP tasks.