Generative AI Course

Module 1: Supervised Learning - Regression ()

• Simple & Multiple Linear Regression
• Polynomial Regression
• Regularization: Ridge, Lasso, ElasticNet
• Assumptions & Diagnostics
• Model Evaluation Metrics: RMSE, MAE, R²

Module 2: Supervised Learning - Classification

• Logistic Regression
• k-Nearest Neighbors (kNN)
• Decision Trees & Random Forest
• Support Vector Machines (SVM)
• Model Evaluation: Confusion Matrix, Precision, Recall, F1-score, ROC-AUC

Module 3: Unsupervised Learning

• Clustering: K-Means, Hierarchical, DBSCAN
• Dimensionality Reduction: PCA, t-SNE
• Association Rule Mining (Apriori)
• Anomaly Detection

Module 4: Ensemble Modelling

• Bagging, Boosting, and Stacking
• Random Forest and Gradient Boosting
• Lambda functions
• XGBoost, LightGBM, CatBoost
• Hyperparameter Tuning and Cross-Validation

Module : Time Series Modelling

• Time Series Components: Trend, Seasonality, Noise
• ARIMA, SARIMA
• Exponential Smoothing
• Forecasting and Evaluation Metrics (MAE, RMSE, MAPE)

Module : Model Evaluation and Deep Learning Fundamentals

• Overfitting vs Underfitting
• Bias-Variance Tradeoff
• Lambda functions
• Model Validation Techniques: Cross-validation, Bootstrapping
• Introduction to Neural Networks and Deep Learning Concepts

Module 1: Neural Network Basics

• Perceptron and Multilayer Perceptron (MLP)
• Activation Functions
• Forward and Backpropagation
• Loss Functions and Gradient Descent

Module 2: Deep Learning Optimisation

• Optimizers: SGD, Adam, RMSProp
• Learning Rate Scheduling
• Regularization Techniques: Dropout, Batch Normalization
• Early Stopping and Check Pointing

Module 3: Convolution Neural Networks (CNN)

• Convolution Operation and Kernels
• Pooling Layers and Flattening
• Popular CNN Architectures: LeNet, VGG, ResNet
• Image Classification and Object Detection

Module 4: Recurrent Neural Networks (RNN)

• RNN Basics and Applications
• LSTM and GRU Networks
• Sequence-to-Sequence Models
• Applications in Text and Time Series

Module 1: Unsupervised Learning Advanced

• Advanced Clustering Techniques
• Autoencoders for Anomaly Detection and Compression
• Variational Autoencoders (VAE)
• Generative Modelling Basics

Module 2: Natural Language Processing (NLP)

• Text Preprocessing: Tokenization, Stemming, Lemmatization
• Word Embeddings: Word2Vec, GloVe, FastText
• Language Models and Seq2Seq
• Text Classification, Summarization, and Named Entity Recognition

Module 1: Generative AI

• Overview of Generative AI Models
• GANs (Generative Adversarial Networks)
• VAEs (Variational Autoencoders)
• Diffusion Models

Module 2: ML Transformers

• Attention Mechanism and Self-Attention
• Transformer Architecture (Encoder, Decoder)
• Applications in NLP and Vision
• Hands-on with Hugging Face Transformers

Module 3: Applications of Generative AI

• Image Generation (StyleGAN, DALL·E)
• Text Generation (GPT, T5)
• Audio and Music Generation
• Multi-modal AI Applications

Module 4: Large Language Models

• Overview of LLMs: GPT, BERT, LLaMA, T5
• Fine-tuning Pretrained Models
• Prompt Engineering
• Applications in Conversational AI

Module 1: Agentic AI

• Concept of Autonomous AI Agents
• Decision Making and Task Execution
• Tool-augmented LLM Agents
• Case Studies: AutoGPT, LangChain Agents

Module 2: Reinforcement Learning

• Fundamentals of RL: Agent, Environment, Reward
• Markov Decision Process (MDP)
• Q-Learning and Deep Q-Networks
• Applications in Games, Robotics, and Optimization

Module 1: Capstone Project

• AI Chatbot with domain knowledge
• Image or Video Generation using GANs/Diffusion Models
• Multi-modal AI Application (Text + Image + Audio)
• Personalized Recommendation Engine
• Deliverables:
  • Project report with architecture, dataset, and results
  • GitHub repository with code and documentation
  • Presentation & Demo