Advanced Certificate Programme in Machine Learning, Gen AI & LLMs for Business Applications

5. Introduction to Deep Learning

5.1 Fundamentals of Neural Networks

• Neurons, Layers, and Activation Functions
• Loss Functions and Optimization

5.2 Deep Learning Architectures

• Convolutional Neural Networks (CNNs)
• Recurrent Neural Networks (RNNs)
• Advanced Architectures: LSTMs, GRUs, Attention Mechanisms

6. Python Tools for Deep Learning

6.1 Introduction to TensorFlow and Keras

• Building Neural Networks with Keras
• Training and Evaluating Deep Learning Models
• Visualizing Model Performance

6.2 PyTorch for Deep Learning

• Understanding Tensors and Autograd
• Implementing CNNs and RNNs with PyTorch
• Transfer Learning and Fine-Tuning Pre-Trained Models

7. Practical Applications of Deep Learning

• Image Classification and Object Detection with CNNs
• Sequence Modeling for NLP Tasks with RNNs
• Advanced Topics: GANs, Autoencoders, and Attention Models

8. Capstone Project: Deep Learning Application

• Problem Statement and Data Preparation
• Model Development and Tuning
• Final Model Evaluation and Presentation

Note: *subject to modifications at a later stage if required, as per the discretion of the faculty.

9. Introduction to Generative AI

9.1 Overview of Generative Models

• GANs, VAEs, and Diffusion Models
• Applications of Generative AI

9.2 Generative Adversarial Networks (GANs)

• GAN Architecture and Training Process
• Implementing GANs with TensorFlow/PyTorch
• Applications of GANs: Image Synthesis, Style Transfer

10. Variational Autoencoders (VAEs) and Diffusion Models

10.1 Understanding VAEs

• Encoder-Decoder Architecture
• Latent Space Representation and Sampling

10.2 Diffusion Models for Generative AI

• Basics of Diffusion Processes
• Implementing Diffusion Models in Python

11. Practical Applications of Generative AI

• Creative AI: Art and Music Generation
• Data Augmentation with Generative Models
• Ethical Considerations in Generative AI

12. Capstone Project: Generative AI Application

• Project Setup and Data Collection
• Model Development and Fine-Tuning
• Final Model Deployment and Presentation

Note: *subject to modifications at a later stage if required, as per the discretion of the faculty.

13. Introduction to Large Language Models (LLMs)

• Evolution of LLMs: From GPT to GPT-4 and Beyond
• Transformer Architecture and Attention Mechanism
• Pre-trained vs. Fine-Tuned LLMs: Differences and Use Cases

14. Fine-Tuning LLMs

• Data Preparation for Fine-Tuning
• Fine-Tuning LLMs with Hugging Face Transformers
• Evaluating and Optimizing Fine-Tuned Models

15. Building Custom AI Agents with LangChain

• Introduction to LangChain for Building AI Agents
• Creating Custom Chains and Workflow Automation
• Integrating LLMs with External APIs

16. Retrieval-Augmented Generation (RAG)

• Understanding RAG Concepts and Architecture
• Implementing RAG with Hugging Face Transformers
• Practical Applications of RAG in QA and Search Systems

17. Capstone Project: LLM and RAG Application

• Project Setup and Data Collection
• Model Development and Fine-Tuning
• Final Model Evaluation and Presentation

Note: *subject to modifications at a later stage if required, as per the discretion of the faculty.

18. Text-Based Applications of LLMs

• Automated Content Creation and Summarization
• Building Conversational Agents and Chatbots
• Sentiment Analysis and Text Classification

19. Image and Video Applications with LLMs

• Text-to-Image Generation with DALL-E and CLIP
• Video Synthesis and Editing with Generative Models
• Combining LLMs with Computer Vision Tasks

20. Audio Applications of LLMs

• Text-to-Speech (TTS) Systems with LLMs
• Music and Sound Generation
• Voice Cloning and Audio Enhancement

21. Capstone Project: Multimodal LLM Application

• Project Proposal and Planning
• Data Collection and Model Development
• Final Integration and Presentation

Note: *subject to modifications at a later stage if required, as per the discretion of the faculty.

22. Multimodal Generative AI Systems

• Integrating Text, Image, and Audio Models
• Case Studies: AI Art, Music Videos, Virtual Worlds
• Developing Cross-Modal Retrieval Systems

23. Customizing and Extending Generative AI Models

• Fine-Tuning LLMs for Multimodal Tasks
• Building End-to-End Multimodal Pipelines
• Deployment Strategies for Multimodal Applications

24. Capstone Project: Integrated Generative AI Application

• Project Planning and Data Collection
• Model Integration and Workflow Design
• Final Testing, Optimization, and Presentation

Note: *subject to modifications at a later stage if required, as per the discretion of the faculty.

25. Introduction to Productionizing AI Models

• Overview of MLOps and Best Practices
• Setting Up CI/CD Pipelines for AI Applications
• Monitoring and Maintaining AI Models in Production

26. Deploying AI Models with Python Tools

• Model Deployment with TensorFlow Serving and TorchServe
• Scaling Applications with Docker and Kubernetes

27. End-to-End Pipeline for LLM and Generative AI Applications

• Text-to-Speech (TTS) Systems with LLMs 
• Music and Sound Generation 
• Voice Cloning and Audio Enhancement