Skip to main content
AI MasterClass
Home
/Course
/
/
HomeAI Ready Course

Week 8 · LLM Post-Training & Building AI Assistants

RL based Fine Tuning

← Previous8.3 Supervised Fine tuningNext →8.5 Pitfalls and Advanced RL

AI Ready Course59 lectures

Week 1The Engine of AI & The Data-Driven Paradigm
  1. 1.1Why Data Driven Paradigm? E.g. Hand Written Digits11m
  2. 1.2Nearest Neighbor Classifier11m
  3. 1.3Linear Classifier11m
  4. 1.4Softmax Classifier13m
  5. 1.5Gradient Descent9m
Week 2Deep Networks & Building a PyTorch Clone
  1. 2.1The Multi-Layer Architecture5m
  2. 2.2The Forward Pass & Loss1m
  3. 2.3Vector Calculus Gradients & Jacobians9m
  4. 2.4Backpropagation - The Chain Rule in Action18m
  5. 2.5Anatomy of a Dense Layer22m
  6. 2.6Activation Function15m
  7. 2.7Dive into Relu12m
  8. 2.8Building Blocks: Cross Entropy23m
  9. 2.9How PyTorch Works Under the Hood7m
Week 3Standing on the Shoulders of Giants & Building RAG
  1. 3.1Transfer Learning: Standing on the Shoulders of Giants19m
  2. 3.2Embeddings, Vector Search, and Retrieval Augmented Generation (RAG)13m
  3. 3.3Babysitting - The Learning Process23m
  4. 3.4Hyperparameter Optimization28m
  5. 3.5Deep Learning 102: Mastering the Convolutional Building Block33m
  6. 3.6Building Blocks - Convolution12m
  7. 3.7Building Block - Max Pool13m
  8. 3.8Cross Entropy vs Mean Square Loss4m
Week 4The Hidden Geometry of Data & Self-Supervised Learning
  1. 4.1Cross Validation and Hyperparameters9m
  2. 4.2Receptive Field of Deep Convolutional Networks4m
  3. 4.3Weight Initialization17m
  4. 4.4LeCun's Cake & The Hidden Geometry of Data13m
  5. 4.5Why High-Dimensional Space is a Lonely Place (The Sea Urchin)20m
  6. 4.6How FaceID Works: Siamese Networks & One-Shot Learning23m
  7. 4.7From Siamese to Triplet Networks: How Google Trained FaceNet14m
Week 5The Deep Learning Revolution & Conquering Time with RNNs
  1. 5.1The Deep Learning Story: From Cat Brains to AlphaFold9m
  2. 5.1-2Why Data, GPUs, and ReLU Changed Everything13m
  3. 5.2CNN Architectures: Evolution of Depth, Width, and Residuals22m
  4. 5.3From Fixed Inputs to Infinite Sequences: Introduction to RNNs13m
  5. 5.4From Vanishing Gradients to LSTMs: Solving the Memory Problem10m
  6. 5.5Sequence-to-Sequence: Encoder-Decoders and the Vanishing Gradient16m
Week 6The Attention Revolution & Building Transformers
  1. 6.1Breaking the Bottleneck: From RNNs to the Attention Revolution7m
  2. 6.2The Trinity of Transformers: Queries, Keys, and Values Explained24m
  3. 6.3Inside the Transformer: How Queries, Keys, and Values Create Meaning9m
  4. 6.4Assembling the Transformer: From Positional Encodings to GPT22m
  5. 6.5The Evolution of the Transformer: From "Attention Is All You Need" to Llama 39m
  6. 6.6Everything is a Transformer: Applying Attention to Images, Audio, and Robots9m
Week 7The Generative AI Era & Building Diffusion Models
  1. 7.1Generative Models17m
  2. 7.2How a Generator Learns3m
  3. 7.3Vanilla GAN Architecture15m
  4. 7.4Vanilla GAN - The Math6m
  5. 7.5Conditional GAN20m
  6. 7.6Evaluating GANs8m
  7. 7.7Autoencoders13m
  8. 7.8Diffusion Models21m
  9. 7.9Diffusion Models - Reverse Process and Training Loop13m
  10. 7.10Diffusion Models - Architecture10m
Week 8LLM Post-Training & Building AI Assistants
  1. 8.1Why do we need to post train LLMs2m
  2. 8.2Post Training LLMs29m
  3. 8.3Supervised Fine tuning14m
  4. 8.4RL based Fine Tuning16m
  5. 8.5Pitfalls and Advanced RL8m
  6. 8.6The Full Pipeline in Practice23m
  7. 8.7Mathematical Reasoning and Tool Calling - Notebook Walkthrough8m
  8. 8.8Mathematical Reasoning and Tool Calling - Notebook 2 Walkthrough18m

Stay ahead in AI.

Fortnightly digest of top podcasts, industry news, practical resources, and masterclass insights.

View Newsletters
AiMasterclass Logo

Stop Prompting AI.
Start Building it.

RAG | Agents | Vision | Shipping

support@aimasterclass.in+91 99055 63532

© 2026 AIMasterClass. All rights reserved.

|
Lectures|Privacy Policy|Terms of Service