#SIGGRAPHAsia | #SIGGRAPHAsia2022
Introduction to Machine Learning and Neural Networks
DescriptionTaught by: Rajesh Sharma
Brought to you by: Siggraph University Life Long Learning [https://university.siggraph.org/]
Rajesh has designed an intermediate level course for attendees to gain a strong understanding of the basic principles of machine learning and neural networks. Using a mix of theory and hands-on practice, Rajesh will help you build intuition around several topics with easy-to-understand explanations and examples from some of the most commonly used algorithms and models including Autoencoders, CNN, GAN, and Transformers.
Course Content:
Prerequisites: https://colab.research.google.com/drive/1rtVUdxOf_VIoqScSY9zgm9ZT9QxEEHtE?usp=share_link
Shared Drive with course content: https://drive.google.com/drive/folders/1Bo4crmpK1Rb1csavyZmt7yDkK85kGOZr
2:00PM - 2:15PM
• Introduction and Course Overview
• Software setup for Hands-on programming
2:15PM - 3:20PM
• What is Machine Learning, What are Neural Networks?
• Framework for Learning: Theory, Intuition, Practice
• Machine Learning Model vs Theoretical Model Example
• Data: Example Housing Prices
• Data Analysis
• General Framework for ML development
• Example: Linear Regression
• Example: Regression with Neural Networks
• Anatomy of a Neural Network
• Theory: Loss Minimization, Gradient Descent
• General Framework for training a Neural Network
• Classification: Example: Flower Type Identification
• Theory: Log Likelihood
3:20PM - 3:30PM: Break
3:30PM - 4:30PM
• Types of Neural Networks
• Example: AutoEncoder, Application to Denoising
• Example: Convolutional Neural Network
• Example: Style Transfer
• Example: Facial Recognition
• Transformer, RNN
• Example: Language Translation
• Transfer Learning
4:30PM - 4:40PM: Break
4:40PM - 5:40PM
• Distributions – Theory
• Variational AutoEncoder
• Latent Space Examination
• Example: Generative Adversarial Network
• Example: Diffusion Model
• Other advances in Machine Learning, Large Scale Training
• Ethical Issues in Machine Learning & AI
• Summary and Next Steps for Additional Learning
Brought to you by: Siggraph University Life Long Learning [https://university.siggraph.org/]
Rajesh has designed an intermediate level course for attendees to gain a strong understanding of the basic principles of machine learning and neural networks. Using a mix of theory and hands-on practice, Rajesh will help you build intuition around several topics with easy-to-understand explanations and examples from some of the most commonly used algorithms and models including Autoencoders, CNN, GAN, and Transformers.
Course Content:
Prerequisites: https://colab.research.google.com/drive/1rtVUdxOf_VIoqScSY9zgm9ZT9QxEEHtE?usp=share_link
Shared Drive with course content: https://drive.google.com/drive/folders/1Bo4crmpK1Rb1csavyZmt7yDkK85kGOZr
2:00PM - 2:15PM
• Introduction and Course Overview
• Software setup for Hands-on programming
2:15PM - 3:20PM
• What is Machine Learning, What are Neural Networks?
• Framework for Learning: Theory, Intuition, Practice
• Machine Learning Model vs Theoretical Model Example
• Data: Example Housing Prices
• Data Analysis
• General Framework for ML development
• Example: Linear Regression
• Example: Regression with Neural Networks
• Anatomy of a Neural Network
• Theory: Loss Minimization, Gradient Descent
• General Framework for training a Neural Network
• Classification: Example: Flower Type Identification
• Theory: Log Likelihood
3:20PM - 3:30PM: Break
3:30PM - 4:30PM
• Types of Neural Networks
• Example: AutoEncoder, Application to Denoising
• Example: Convolutional Neural Network
• Example: Style Transfer
• Example: Facial Recognition
• Transformer, RNN
• Example: Language Translation
• Transfer Learning
4:30PM - 4:40PM: Break
4:40PM - 5:40PM
• Distributions – Theory
• Variational AutoEncoder
• Latent Space Examination
• Example: Generative Adversarial Network
• Example: Diffusion Model
• Other advances in Machine Learning, Large Scale Training
• Ethical Issues in Machine Learning & AI
• Summary and Next Steps for Additional Learning
Presenter
Event Type
Courses
TimeTuesday, 6 December 20222:00pm - 5:45pm KST
LocationRoom 322, Level 3, West Wing
