Topics from the video
https://youtu.be/nUqgjQs5pJk?si=qZMz7JUd4STb8CKG
(with time location)
- AI Engineering (0:24)
- Foundation Models (1:00)
- Large Language Models (LLMs) (1:26)
- Transformer Architecture (1:57)
- Attention Mechanism (2:25)
- Model Learning & Parameters (3:47)
- Model Parameters (3:53)
- Hyperparameters (4:10)
- Temperature (4:13)
- Top K and Top P (4:31)
- Tokens (5:01)
- Model Context (5:27)
- Prompt Engineering (6:03)
- System Prompt (6:28)
- User Prompt (6:34)
- Zero-shot Learning (6:50)
- Few-shot Learning (6:57)
- In-context Learning (7:09)
- Model Adaptation & Optimization
- Fine-tuning (7:19)
- Parameter Efficient Fine-tuning (PEFT) (7:45)
- LoRA (8:02)
- Quantization (8:10)
- Distillation (8:20)
- Preference Fine-tuning (8:40)
- Retrieval Augmented Generation (RAG) (9:03)
- Embeddings (9:21)
- Vector Database (9:37)
- Chunking (9:54)
- Ranking (10:07)
- Model Architecture Components
- Encoders and Decoders (11:16)
- AI Agents & Tools (10:38)
- Agents (10:40)
- Tools (10:56)
- Model Deployment & Performance
- Inference (11:33)
- Online Inference (11:47)
- Batch Inference (11:55)
- Latency (12:08)
- Streaming (12:18)
- Model Evaluation
- Model Benchmarks (12:30)
- Metrics (12:47)
- Perplexity (12:52)
- BLEU (13:07)
- ROUGE (13:20)
- LLM as Judge (13:45)
- System Integration
- Model Context Protocol (MCP) (14:04)
