1
NEURAL COMPUTERS
PRESENTED BY JAMES OSEI AMPOFO
2
TABLE OF CONTENT
Introduction
Overview
Artificial Neural Networks
Connection Types of Neural Networks
Topology
Types Of Neural Networks
Advantages
Disadvantages
Applications
Conclusion
3
INTRODUCTION
Alexander Bain (1873) claimed that both thoughts and body activity
resulted from interactions among neurons within the brain.
For Bain, every activity led to the firing of a certain set of neurons.
It is now apparent that the brain is exceedingly complex and that
the same brain can handle multiple problems and inputs. ANN is
composed of a large number of highly interconnected processing
elements(neurons) working in unison to solve specific problems.
Neural Network theory has served both:
-better identify how the neurons in the brain function and
-provide the basis for efforts to create artificial intelligence
4
NEURAL COMPUTERS
Neural Computer are computer that uses neural networks in it
operations.
NEURAL NETWORKS: are networks that operates in a manner
inspired by the natural neural network in the brain.
a neural network system is composed of many simple processing
elements operating in parallel whose function is determined by
network structure, connection strengths, and the processing
performed at computing elements or nodes.
5
OVERVIEW
The brain is said to be composed of natural neural networks i.e,
mass of inter-connected computational units called neurons
Each neuron is connected to other neurons.
The human nervous system can be broken down into three stages
that may be represented in block diagram form as: – The receptors
collect information from the environment – e.g. photons on the
retina. – The effectors generate interactions with the environment
– e.g. activate muscles. – The flow of information/activation is
represented by arrows – feed forward and feedback.
Neural
Stimulus Receptors Networks/B Effectors
rain
6
OVERVIEW
The Structure of a Biological neuron
A biological neuron has three types of main
components; dendrites, soma (or cell body)
and axon.
Dendrites receives signals from other neurons.
The soma, sums the incoming signals. When
sufficient input is received, the cell fires; that is it
transmit a signal over its axon to other cells.
7
ARTIFICIAL NEURAL NETWORK
An Artificial Neural Network (ANN) is an information processing
paradigm that is inspired by the way biological nervous systems,
such as the brain, process information.
The key element of this paradigm is the novel structure of the
information processing system.
It is composed of a large number of highly interconnected
processing elements (neurons) working in unison to solve specific
problems.
An ANN is configured for a specific application, such as pattern
recognition or data classification, through a learning process.
8
WORKING OF ARTIFICIAL NEURON
An artificial neuron also contains dendrites, cell body, axon and
synapse.
In artificial neural networks, the inputs are taken only when
threshold value is satisfied. Otherwise inputs are not taken by the
neuron..
These are two modes of neurons such as, training mode and using
mode.
9
10
TOPOLOGY
Topologies in Neural networks:
Topology defines how a neuron in neural network connect with
another neurons.
There are three types of topologies every neural network must
follow
1. single-level topology
2. multi-level topology
3. recurrent topology
11
Single-level topology
The simplest kind of neural network is a single-layer network,
which consist of equal number of input and output nodes.
12
Multi-level
In multi-level, each neuron in one layer has directed connections
to the neurons of the subsequent layer.
13
recurrent
A recurrent neural networks(RNN) is a class of artificial neural
networks where connections between units form a directed cycles.
14
CONNECTION TYPES IN NEURAL NETWORKS
Neurons are interconnection with each other, for the transferring
the data.
There are two types of hierarchies for connecting the neurons
-Static connection
-Dynamic connection
15
1.Static(feed forward)
The feedforward neural network was the first and most simple
type of artificial neural network.
In this network, the information will move in one direction only.
16
2. Dynamic(feed backward)
Feed backwards is advanced than feed forward.
In feed backward, looping mechanism is introduced.
17
TYPES OF NEURAL NETWORKS
Feedforward Neural Network – Artificial Neuron: ...
Radial basis function Neural Network: ...
Recurrent Neural Network(RNN) – Long Short Term Memory: ...
Modular Neural Network:
18
ADVANTAGES
It is used in developing predictive models for dichotomous
outcome in medicine.
Collective computation : The network performs routinely many
operations in parallel and also given task in a distributed manner.
Flexibility : The network automatically adjust to a new
environment without using any programmed instruction.
Work by learning
No need to write algorithms.
19
DISADVANTAGES
It has a black box nature.
Requires high processing time for large neural networks.
20
APPLICATION
Image recognition
Natural language processing, translation and language generation
Stock market prediction
Drug discovery and development
21
CONCLUSION
In conclusion, the idea of neural network just tries to modify
computers to work just like the human brain with the use of
neurons.
22
Reference
https://www.britannica.com/technology/neural-network
https://slideplayer.com/slide/13271589/
https://towardsdatascience.com/multi-layer-neural-networks-with-sigmoid-function-deep-l
earning-for-rookies-2-bf464f09eb7f
23
Appreciate
THANK YOU
