Dive into the fundamentals of training neural networks in this comprehensive lecture from the University of Central Florida's Computer Vision course. Explore key concepts including network parameters, convolutional neural networks (CNNs), learning phases, and the process of minimizing cost through gradient descent. Gain insights into loss functions, differentiability, and the crucial backpropagation technique using the chain rule. Witness an optimization demo and understand the principles of stochastic gradient descent. Perfect for students and professionals seeking to deepen their understanding of deep learning applications in computer vision.

Syllabus

Intro
UCF Network Parameters - recap
Convolution - Intuition
General CNN architecture - recap
Learning phases - recap Images
Network Training - Minimize Cost
General approach
Train CNN with Gradient Descent
Loss Functions
Differentiability
Backpropagation - Chain Rule
Optimization demo
Stochastic Gradient Descent