This course on Convolutional Neural Networks aims to teach learners about deep computer vision. By the end of the course, students will be able to understand tasks in computer vision, detect high-level features, extract features manually and through learning, use fully connected neural networks, apply filters for feature extraction, and work with convolutional layers and feature maps. The course covers topics such as local connectivity, non-linearity, pooling, classification, training with backpropagation, and applications in various fields like semantic segmentation, self-driving cars, and healthcare. The teaching method includes lectures, slides, and lab materials, making it suitable for individuals interested in deep learning and computer vision.
Overview
Syllabus
Intro
Images are Numbers
Tasks in Computer Vision
High Level Feature Detection
Manual Feature Extraction
Learning Feature Representations
Fully Connected Neural Network
Using Spatial Structure
Applying Filters to Extract Features
Feature Extraction with Convolution
Filters to Detect X Features
The Convolution Operation
Producing Feature Maps
Convolutional Layers: Local Connectivity
Introducing Non-Linearity
Pooling
CNNs for Classification: Feature Learning
CNNs for Classification: Class Probabilities
CNNs: Training with Backpropagation
ImageNet Dataset
ImageNet Challenge: Classification Task
An Architecture for Many Applications
Beyond Classification
Semantic Segmentation: FCNs
Driving Scene Segmentation
Image Captioning using RNNS
Impact: Face Detection
Impact: Self-Driving Cars
Impact: Healthcare
Deep Learning for Computer Vision: Summary
Taught by
https://www.youtube.com/@AAmini/videos
