MTH101 - Mathematics for Data Science

• Overview of AI and ML:

  Introduction to AI history, philosophy, and its significance in solving complex problems in various domains.

• Mathematical Foundations:

  Linear algebra, calculus, probability, and statistics essentials for AI and ML.

CS101 - Programming for Data Engineering

• Data Manipulation and Analysis

  Dive into Pandas for data manipulation: DataFrames, series, data cleaning, and preprocessing techniques.

• Data Visualization Techniques

  Get creative with Matplotlib and Seaborn: Crafting plots, histograms, scatter plots, and interactive visualizations to tell stories with data.

ML101 - Machine Learning Fundamentals

• Supervised Learning:

  Understanding the principles of supervised learning algorithms including linear regression, logistic regression, and basic classification algorithms.

• Unsupervised Learning:

  Introduction to clustering, dimensionality reduction techniques, and association rule mining.

• Ensemble Techniques and Model Selection:

  Boosting, bagging, random forest, and bias-variance trade-off.

• Evaluation Metrics:

  Metrics for assessing model performance including accuracy, cover precision, recall, F1 score, and ROC-AUC curve.

ML201 - Deep Learning and Neural Networks

• Neural Network Fundamentals:

  Basics of neural networks, activation functions, and architecture design.

• Deep Learning Algorithms:

  Introduction to Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), and Transformers.

• Frameworks and Tools:

  Practical sessions on TensorFlow and PyTorch for building and training deep learning models.

• Advanced Learning Techniques:

  Multi-task learning, self-supervised learning, transfer learning, and consistency regularization.

• Reinforcement Learning:

  Basics of reinforcement learning, policy optimization, and applications in game playing and robotics.

AI101 - Specialized Topics in AI and ML

• Deep Dive into Generative Adversarial Networks (GANs):

  Understanding the architecture and working principles of GANs. Applications of GANs in image generation, style transfer, and more. Hands-on projects involving training simple GANs for specific generation tasks.

• Natural Language Processing (NLP):

  Techniques for text processing, sentiment analysis, machine translation, and chatbot development.

• Computer Vision:

  Fundamentals of image processing, object detection, facial recognition, and image generation with Generative Adversarial Networks (GANs).

• Advanced Generative Models:

  Scene Graphs, and Probabilistic Diffusion Models.

• Exploring Variational Autoencoders (VAEs):

  Introduction to the concept of autoencoders and their use in generative AI. Detailed look at VAEs and their applications in generating high-quality, diverse data samples.

• Large Language Models (LLMs):

  Comprehensive overview of the architecture, training processes, and capabilities of large language models like GPT (Generative Pretrained Transformer) and BERT (Bidirectional Encoder Representations from Transformers). Discussion on their applications in natural language understanding, text generation, and conversational AI.