Explore the powerful world of autoencoders in this 32-minute video lecture. Dive into dimensionality reduction, denoising autoencoders, and variational autoencoders. Learn about generative models, dataset handling, and linear methods. Gain insights into deep learning and neural networks, including perceptrons and sigmoid functions. Discover how autoencoders function as generators and explore the concept of latent space. Master the training process for neural networks and autoencoders, focusing on loss functions and reconstruction techniques. Access a GitHub repository for hands-on practice and explore recommended videos on related topics such as generative adversarial networks and recurrent neural networks to enhance your understanding of machine learning concepts.
Overview
Syllabus
Intro:
Dimensionality reduction
Denoising autoencoders
Variational autoencoders
Training autoencoders
Introduction
Generative models
Variational autoencoders
Dataset of images
Denoising autoencoders
Linear methods
A friendly introduction to deep learning and neural networks
Mapping the real numbers to the interval 0,1
Sigmoid function
Perceptron
Correct noise
Autoencoders as generators
Latent space
Training a neural network - loss function
Training an autoencoder
Training autoencoders
Reconstruction loss Mean squared error
Reconstruction loss log-loss
Training a variational auto encoder
Taught by
Serrano.Academy
