Convolutional Neural Networks

Explore the fundamentals of Convolutional Neural Networks (CNNs) for computer vision in this comprehensive lecture from MIT's Introduction to Deep Learning course. Delve into the world of visual feature learning, understanding how computers perceive images and the process of feature extraction through convolution. Examine the architecture of CNNs, including non-linearity and pooling layers, and witness their practical implementation through an end-to-end code example. Discover the wide-ranging applications of CNNs, from object detection to autonomous driving, and gain insights into the transformative impact of deep learning on computer vision tasks. This 55-minute lecture, delivered by Alexander Amini, provides a thorough overview of CNNs, equipping you with essential knowledge to leverage these powerful tools in various computer vision applications.

​ - Introduction
​ - Amazing applications of vision
- What computers "see"
- Learning visual features
​ - Feature extraction and convolution
- The convolution operation
​ - Convolution neural networks
​ - Non-linearity and pooling
- End-to-end code example
​ - Applications
- Object detection
- End-to-end self driving cars
​ - Summary