MULTILAYER NETWORK SYSTEM

Neural networks represent deep learning using artificial

intelligence. Certain application scenarios are too heavy or
out of scope for traditional machine learning algorithms to
handle. As they are commonly known, Neural Network
pitches in such scenarios and fills the gap.
EXAMPLE OF MULTILAYER NETWORK

 Artificial neural networks are inspired from the biological

neurons within the human body which activate under certain
circumstances resulting in a related action performed by the
body in response. Artificial neural nets consist of various layers
of interconnected artificial neurons powered by activation
functions which help in switching them ON/OFF.
INPUT,HIDDEN AND OUTPUT LAYER

 Input layer represents dimensions of the input vector.

 Hidden layer represents the intermediary nodes that divide the
input space into regions with (soft) boundaries. It takes in a set
of weighted input and produces output through an activation
function.
 Output layer represents the output of the neural network.
TYPES OF NEURAL NETWORK

 There are many types of neural networks available or that might be

in the development stage. They can be classified depending on
their: Structure, Data flow, Neurons used and their density, Layers
and their depth activation filters etc.
 We are going to discuss the following neural networks:
1. Feed Forward Neural Networks
2. Multilayer Perception
3. Convolutional neural Network
4. Sequence to Sequence Models
 FEED FORWARD NEURAL NETWORKS

Applications on Feed Forward Neural Networks:

 Simple classification (where traditional Machine-learning based classification
algorithms have limitations)
 Face recognition [Simple straight forward image processing]
 Computer vision [Where target classes are difficult to classify]
 Speech Recognition
The simplest form of neural networks where input data travels in one direction
only, passing through artificial neural nodes and exiting through output nodes. Where
hidden layers may or may not be present, input and output layers are present there.
Based on this, they can be further classified as a single-layered or multi-layered feed-
forward neural network.
Number of layers depends on the complexity of the function. It has uni-
directional forward propagation but no backward propagation .
ADVANTAGES AND DISADVANTAGES
OF FEED FORWARD
Advantages of Feed Forward Neural Networks
 Less complex,
 easy to design &
 Maintain
 Fast and speedy [One-way propagation]
 Highly responsive to noisy data
Disadvantages of Feed Forward Neural Networks:
 Cannot be used for deep learning [due to absence of dense layers and back
propagation]
MULTI-LAYER PERCEPTION

Applications on Multi-Layer Perceptron

 Speech Recognition
 Machine Translation
 Complex Classification
An entry point towards complex neural nets where input data travels
through various layers of artificial neurons. Every single node is connected to all
neurons in the next layer which makes it a fully connected neural network. Input
and output layers are present having multiple hidden Layers i.e. at least three or
more layers in total. It has a bi-directional propagation i.e. forward propagation and
backward propagation.
ADVANTAGES AND DISADVANTAGES
MULTI-LAYER PERCEPTION
Advantages on Multi-Layer Perceptron
 Used for deep learning [due to the presence of dense fully connected layers and
back propagation] 
Disadvantages on Multi-Layer Perceptron:
  Comparatively complex to design and maintain
 Comparatively slow (depends on number of hidden layers)
 CONVOLUTIONAL NEURAL NETWORK

Convolution neural network contains a three-dimensional arrangement of neurons,

instead of the standard two-dimensional array. The first layer is called a
convolutional layer.
Applications on Convolution Neural Network
Image processing
Computer Vision
Speech Recognition
Machine translation
ADVANTAGES AND DISADVANTAGES
OF CONVOLUTION NEURAL NETWORK
Advantages of Convolution Neural Network:
 Used for deep learning with few parameters
 Less parameters to learn as compared to fully connected layer
Disadvantages of Convolution Neural Network:
 Comparatively complex to design and maintain
 Comparatively slow [depends on the number of hidden layers]
SEQUENCE TO SEQUENCE

 A sequence to sequence model consists of two Recurrent Neural Networks. Here,

there exists an encoder that processes the input and a decoder that processes the
output.
The encoder and decoder work simultaneously – either using the same parameter
or different ones.
In those cases where the length of the input data is equal to the length of the
output data. While they possess similar benefits and limitations of the RNN, these
models are usually applied mainly in chatbots, machine translations, and question
answering systems.
WHAT IS CNN AND DNN?
A deep neural network (DNN) is an artificial neural
network (ANN) with multiple layers between the input
and output layers. They can model complex non-linear
relationships.
Convolutional Neural Networks (CNN) are an
alternative type of DNN that allow modelling both time
and space correlations in multivariate signals.
DEEP AND CONVOLUTIONAL NETWORK

 Deep learning definition: A subfield of machine learning that structures

algorithms in layers to create an “artificial neural network” that can learn
and make intelligent decisions on its own.
 Convolutional neural networks (CNNs) are algorithms specifically designed
for image processing and object detection. The “convolution” is a unique
process of filtering through an image to assess every element within it.
CNNs are often used to power computer vision, a field of AI that teaches
machines how to process the visual world. Facial recognition technology is a
common use of computer vision.
EXAMPLE OF CONVOLUTIONAL
NEURAL NETWORK

 Examples of CNN in computer vision are face

recognition, image classification etc. It is similar
to the basic neural network. CNN also have
learnable parameter like neural network i.e,
weights, biases etc.