Scribd
Upload
23 views11 pages

Unit 2 Variational Auto Encoder

Variational Autoencoders (VAEs) are generative models in Machine Learning that create new data based on input patterns, consisting of an encoder and a decoder. The encoder learns important features and generates a probabilistic representation of the data, while the decoder reconstructs the input or generates new data. VAEs introduce randomness in the latent space, allowing for the creation of varied yet realistic data outputs.

Uploaded by

AYUSH CHAUHAN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
23 views11 pages

Unit 2 Variational Auto Encoder

Variational Autoencoders (VAEs) are generative models in Machine Learning that create new data based on input patterns, consisting of an encoder and a decoder. The encoder learns important features and generates a probabilistic representation of the data, while the decoder reconstructs the input or generates new data. VAEs introduce randomness in the latent space, allowing for the creation of varied yet realistic data outputs.

Uploaded by

AYUSH CHAUHAN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

UNIT 2

Variational AutoEncoders

By: Prof. Rajesh R M


Assistant Professor
Dept. of AI and ML
RVCE, Bangalore
Variational AutoEncoders

Variational Autoencoders (VAEs) are generative models in Machine Learning (ML) that create new
data similar to the input they are trained on. Along with data generation they also perform common
autoencoder tasks like denoising. Like all autoencoders

VAEs consist of:


•Encoder: Learns important patterns (latent variables) from input data.
•Decoder: It uses those latent variables to reconstruct the input.
Variational AutoEncoders

 Traditional Autoencoders that encode a fixed representation .

 VAEs learn a continuous probabilistic representation of latent space.

 VAE is a special kind of autoencoder that can generate new data instead of just compressing and
reconstructing it.
Variational AutoEncoders

VAE Main Parts


1. Encoder (Understanding the Input)
•The encoder takes the input data like an image or text
and tries to understand its most important features.

•Instead of creating a fixed compressed version like a


normal autoencoder it creates two things:
• Mean (μ): A central value representing the
data.
• Standard Deviation (σ): It is a measure of
how much the values can vary.
•These two values define a range of possibilities instead
of a single number.
Variational AutoEncoders

VAE Main Parts


1. Encoder (Understanding the Input)
The Multivariate Normal Distribution
A normal distribution (or Gaussian distribution) μ, σ is a probability distribution characterized by a
distinctive bell curve shape, defined by two variables: the mean (μ) and the variance (σ2). The standard
deviation (sigma) is the square root of the variance.
The probability density function of the normal distribution in one dimension is:

We can sample a point z from a normal distribution with mean μ and standard deviation
σ using the following equation:
Variational AutoEncoders

VAE Main Parts


1. Encoder (Understanding the Input)
To summarize, the encoder will take each input image and encode it to two vectors that together define a multivariate
normal distribution in the latent space:
z_mean
The mean point of the distribution
z_log_var
The logarithm of the variance of each dimension
We can sample a point z from the distribution defined by these values using the following equation:
z = z_mean + z_sigma * epsilon
where:
z_sigma = exp(z_log_var * 0.5)
epsilon ~ N(0,I)
Variational AutoEncoders

VAE Main Parts


1. Encoder (Understanding the Input)

VAE architecture diagram


Variational AutoEncoders

VAE Main Parts


2. Latent Space (Adding Some Randomness)
 Instead of encoding input into a fixed number VAEs introduce randomness to create variations.
 The model picks a point from the range to create different variations of the data.
 This is what makes VAEs great for generating new slightly different but realistic data.
Variational AutoEncoders

VAE Main Parts


2. Latent Space (Adding Some Randomness)
Variational AutoEncoders

2. Latent Space (Adding Some Randomness)


Variational AutoEncoders
3. Decoder (Reconstructing or Creating New Data)
The decoder takes this sampled value and tries to reconstruct the original input.
Since the encoder creates a range of possibilities instead of a fixed number the decoder can generate new similar data
instead of just memorizing the input.

You might also like