Machine Learning Lectures


Team Projects

Lecture 1. Introduction to Machine Learning and Reinforcement Learning

Lecture 2. Perceptron and Forward Propagation

Lecture 3. Back Propagation I

Lecture 4. Back Propagation II

Lecture 5. Entropy and Cost Function I

Lecture 6. Entropy and Cost Function II

Lecture 7. Softmax and Regressions

Lecture 8. Machine Learning Design and Performance

Lecture 9. Overview of Deep Reinforcement Learning and Alphago

Lecture 10. Recurrent Neural Network (RNN) Architecture

Lecture 11. Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM)

Lecture 12. Machine Learning using Python and TensorFlow

Lecture 13. Introduction to AI Engineering Research in TERA LAB

Lecture 14. RNN Back Propagation Through Time


Lecture 15. LSTM Back propagation and Transformer Learning

Lecture 16. CNN Architectures

Lecture 17. Autoencoder and GAN

Lecture 18. Introduction of GAN and GPT-3

Lecture 19. Markov Decision Process and Bellman Equation

Lecture 20. Model based Prediction and Control

Lecture 21. Monte Carlo Method and Temporal Difference Method

Lecture 22. Value Based DNN Agent

Lecture 23. Policy Based DNN Agent

Lecture 24. Introduction to Deep Reinforcement Learning and DRL-based SI/PI Design

Lecture 25. Introduction to GPU and HBM Architecture to Accelerate AI Application

Final Term Project Presentations

Team 1

Reinforcement Learning-based Design of Passive Equalizer for Memory Channel in High Bandwidth Memory by using DNN-based Environment

Team 2

Deep Reinforcement Learning (DRL)-based Differential Channel Design Optimization Method

Team 3

Search-based Combinatorial Optimization Algorithms and its Application to Small Grid Routing

Team 4

Evaluation of Various Neural Network-based Policy Parameterization Models for DRL-based Power Distribution Network Decoupling Capacitor Placement Optimization

Team 5

Machine Learning-based Channel Optimization on High Bandwidth Memory (HBM)