YoVDO

Vision Transformer - Lecture 14

Offered By: MIT HAN Lab via YouTube

Tags

Vision Transformers Courses Deep Learning Courses Computer Vision Courses Image Classification Courses Transfer Learning Courses Attention Mechanisms Courses Self-Attention Courses Positional Encoding Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the cutting-edge world of Vision Transformers in this comprehensive lecture from MIT's 6.5940 course on Efficient Machine Learning. Delve into the revolutionary application of transformer architectures to computer vision tasks, guided by Professor Song Han. Learn about the key principles, advantages, and implementation details of Vision Transformers, understanding how they differ from traditional convolutional neural networks. Discover the latest advancements in this rapidly evolving field and gain insights into how Vision Transformers are reshaping the landscape of image recognition, object detection, and other visual AI applications. Access accompanying slides for enhanced learning and visual aids to reinforce complex concepts. Perfect for students, researchers, and professionals seeking to expand their knowledge in advanced machine learning techniques for computer vision.

Syllabus

EfficientML.ai Lecture 14 - Vision Transformer (MIT 6.5940, Fall 2023)


Taught by

MIT HAN Lab

Related Courses

Generative AI Language Modeling with Transformers
IBM via Coursera
Transformers Explained - Part 1: Generative Music AI
Valerio Velardo - The Sound of AI via YouTube
Attention Is All You Need
Yannic Kilcher via YouTube
Attention Is All You Need - Transformer Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube
Attention with Linear Biases Explained
Unify via YouTube