Fundamentals of Generative AI - Ace the AI Engineer Interviews

0% completed

All LessonsFree Lessons (4)

Introduction

Course Overview

Neural Network Training and Optimization

Neural Networks Training Gradient Descent Transfer Learning Model Alignment Model Compression Fine-Tuning Synthetic Data Generation

Embeddings and Tokenization

Embeddings Tokenization Methods Beam Search

Attention Mechanisms

Multi-Head Self-Attention Cross-Attention Flash Attention Positional Encodings Masking Normalization in Transformers

Evaluation Techniques

Perplexity BLEU and ROUGE

Model Architectures and Comparisons

Choosing Between Different Types of AI Models Scaling Laws Elo Rating Systems for LLMs Diffusion Models Model Interpretability Hallucinations and Jailbreaks How ChatGPT Works?

Learning Techniques

Few-Shot Learning Chain-of-Thought Prompting RAG for LLMs Choosing Between RAG, ICL, and Fine-Tuning In LLMs

Scalability and Efficiency

Mixture of Experts Vector Databases Agentic Errors

Wrap Up

Fundamentals of Generative AI

Practice Mock Interview