From Autoencoders to Variational Autoencoders - Improving the Encoder
Offered By: Valerio Velardo - The Sound of AI via YouTube
Course Description
Overview
Explore the transformation of autoencoders into Variational Autoencoders (VAEs) in this informative video. Delve into the limitations of traditional autoencoders for generative tasks and discover how VAEs address these issues. Learn about multivariate normal distributions and their crucial role in encoding input data into a latent space for improved generative capabilities. Gain insights into the encoder mapping differences between autoencoders and VAEs, understand univariate and multivariate normal distributions, and explore how multivariate normal distributions solve discontinuities in VAEs. Perfect for those interested in deep learning and generative models in artificial intelligence and sound processing.
Syllabus
Intro
Issues with vanilla AEs
From AEs to VAEs
Encoder mapping: AEs vs VAEs
Univariate normal distribution
Multivariate normal distrivution
Usage of multivariate normal distribution in VAEs
How multivariate normal distribution solves discontinuities in VAEs
Taught by
Valerio Velardo - The Sound of AI
Related Courses
Visual Recognition & UnderstandingUniversity at Buffalo via Coursera Deep Learning for Computer Vision
IIT Hyderabad via Swayam Deep Learning in Life Sciences - Spring 2021
Massachusetts Institute of Technology via YouTube Advanced Deep Learning Methods for Healthcare
University of Illinois at Urbana-Champaign via Coursera Generative Models
Serrano.Academy via YouTube