Chapter
Unit IV
04
Networking AutoEncoder
and
Security
Hours: 06
Presented by:
Prof.S.S.Bhosale
PREC, Loni
.
Course Outcomes
CO2:
.
Types of Autoencoder
1. UnderComplete Autoncoder:
• An autoencoder whose code dimension is less
than input dimensions is called undercomplete
autoencoder
• Goal of the Autoencoder is to capture the most
important features present in the data.
• Undercomplete autoencoders have a smaller
dimension for hidden layer compared to the input
layer.
.
Types of Autoencoder
•This helps to obtain important features from the data.
•Objective is to minimize the loss function by
penalizing the g(f(x)) for being different from the
input x.
•When decoder is linear and we use a mean squared
error loss function then undercomplete autoencoder
generates a reduced feature space similar to PCA.
.
Types of Autoencoder
• Undercomplete autoencoders do not need any
regularization as they maximize the probability of
data rather than copying the input to the output.
.
Types of Autoencoder
.
Contractive Autoencoders(CAE):
Contractive autoencoder(CAE) objective is to
have a robust learned representation which is
less sensitive to small variation in the data.
Robustness of the representation for the data is
done by applying a penalty term to the loss
function.
.
Contractive Autoencoders(CAE):
Contractive autoencoder is another
regularization technique like sparse
autoencoders and denoising autoencoders.
CAE surpasses results obtained by regularizing
autoencoder using weight decay or by
denoising.
.
Types of Autoencoder
CAE is a better choice than denoising
autoencoder to learn useful feature extraction.
Penalty term generates mapping which are
strongly contracting the data and hence the
name contractive autoencoder.
.
Contractive Autoencoders(CAE):
.
Variational autoencoder :
Variational autoencoder can be defined as being
an autoencoder whose training is regularised to
avoid overfitting and ensure that the latent space
has good properties that enable generative
process.
.
Types of Autoencoder
•Just as a standard autoencoder, a variational
autoencoder is an architecture composed of both
an encoder and a decoder and that is trained to
minimize the reconstruction error between the
encoded-decoded data and the initial data.
• In order to be able to use the decoder of our
autoencoder for generative purpose, we have to
be sure that the latent space is regular enough.
.
Types of Autoencoder
One possible solution to obtain such regularity
is to introduce explicit regularisation during the
training process.
.
Types of Autoencoder
.
Types of Autoencoder
.
Stochasic Autoencoder:
In this autoencoder both encoder and decoder
are not simple functions but instead involved
some noise injection.
.
Types of Autoencoder
.
Types of Autoencoder
Stacked Autoencoder (Deep Autoencoder):
Stacked Autoencoder are the typical and the
most basic form of autoencoder .
Just like other neural networks autoencoder can
have multiple hidden layers.
Such autoencoder are called as Stacked
Autoencoder or deep autoencoder .
.
Types of Autoencoder
Adding more layers helps the autoencoder to
learn more complex codings.
Autoencoder is a kind of unsupervised learning
structure that owns three layers: input layer,
hidden layer, and output layer.
The process of an autoencoder training consists
of two parts: encoder and decoder.
.
Types of Autoencoder
Encoder is used for mapping the input data into
hidden representation, and decoder is referred to
reconstructing input data from the hidden
representation.
The stacked autoencoders are, as the name
suggests, multiple encoders stacked on top of
one another.
.
Types of Autoencoder
.
Types of Autoencoder
