Course for Generative AI

• NLP & LLMs: Fundamentals of transformers, GPT, BERT, embeddings, prompt engineering, and retrieval-augmented generation (RAG).
• Building LLM Applications: Working with APIs, LangChain, and developing AI-powered chatbots and agents.
• Fine-Tuning & Optimization: Pre-training, LoRA/QLoRA, reinforcement learning, and reasoning models.
• Image & Video Generation: Creating and editing images using Stable Diffusion, DALL·E, and Midjourney, and exploring AI-powered video synthesis.
• Vision-Language & Multimodal AI: Working with CLIP, LLaVa, and GPT-4V to connect text, images, and audio.
• Speech & Audio AI: Speech-to-text (ASR) with Whisper and text-to-speech (TTS) models.
• Deployment & Real-World Applications: Optimizing AI models, ensuring scalability, and addressing ethical concerns.
• Final Project: Building and presenting a real-world AI-powered application.

By the end of this course, students will be proficient in text, image, speech, and video generation with generative AI, will have hands-on experience fine-tuning & optimizing generative AI models and will be able to develop and deploy AI-powered applications.

• Python
• IDE (Spyder)
• Jupyter Notebook
• Google Colab where a GPU is required

All required tools are free, and instructions for downloading and installing them will be provided at the start of the program.