Scribd
Upload
98 views17 pages

Artificial Neural Network Final - 3

This document discusses artificial neural networks (ANNs). ANNs are mathematical models inspired by biological neural networks. They are non-linear tools used to model complex relationships between inputs and outputs or find patterns in data. The document outlines characteristics of ANNs like nonlinearity, input-output mapping, adaptivity, and fault tolerance. It also discusses applications like function approximation, classification, data processing, and more.

Uploaded by

Priyasmita Dasgupta
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
98 views17 pages

Artificial Neural Network Final - 3

This document discusses artificial neural networks (ANNs). ANNs are mathematical models inspired by biological neural networks. They are non-linear tools used to model complex relationships between inputs and outputs or find patterns in data. The document outlines characteristics of ANNs like nonlinearity, input-output mapping, adaptivity, and fault tolerance. It also discusses applications like function approximation, classification, data processing, and more.

Uploaded by

Priyasmita Dasgupta
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 17

Artificial Neural Network

Presented by
•Sohini Dey
•Ananya Saha
•Shamim Parvin
•Priyasmita Dasgupta
Artificial Neural Network
So, What is it?
What is ANN?

An artificial neural network (ANN), usually called neural


network (NN), is a mathematical model or computational
model that is inspired by the structure and/or functional
aspects of biological neural networks

Modern neural networks are non-linear statistical data


modeling tools. They are usually used to model complex
relationships between inputs and outputs or to find patterns in
data.
Brain: a highly complex, linear and parallel
computer
• Storage capacity
– brain has more neurons than computer has bits
• Speed
– brain is much slower than a computer
• a silicon IC has response time 10-9 sec compared to processing speed of a
human neuron is 10-6 sec
• Brain relies on massive parallelism for performance:
• 10billions of neurons with 60 trillions of interconnections
• The brain is more suited to intelligence processing and learning
Neural Network Characteristics

• Nonlinearity (Interconnection of non linear neurons)


• Input Output Mapping (Learning with a teacher)
• Adaptivity (can adapt the free parameters to changes in surroundings)
• Evidential Response (decision with a measure of confidence)
• Fault Tolerance (Graceful Degradation)
• VLSI Implementability
• Neuro Biological Analogy
Pyramidal Cell
Synapse Concept
The synapse resistance to the incoming
signal can be changed during a "learning"
process [1949]

Hebb’s Rule:
If an input of a neuron is repeatedly and persistently
causing the neuron to fire, a metabolic change
happens in the synapse of that particular input to
reduce its resistance
Equivalent Electrical Model
Linear threshold (Step function)
And what about non-linearity?
• Logistic functions are often used in neural networks to introduce
nonlinearity in the model
Network function

An ANN is typically defined by three types of


parameters:
• The interconnection pattern between different
layers of neurons
• The learning process for updating the weights of
the interconnections
• The activation function that converts a neuron's
weighted input to its output activation.
Neural networks and neuroscience
• Theoretical and computational neuroscience is the
field concerned with the theoretical analysis and
computational modeling of biological neural systems.

• The aim of the field is to create models of biological


neural systems in order to understand how biological
systems work.)
Several softwares on Neural Network have been developed .
Commercial Software-
• Statistica Neural Network
• TNs2Server
• DataEngine
• Know Man Basic Suit
• Partrek
• Saxon
• Neurogen

Freeware Software-
• Net II
• NeuDC
• PlaNet
• Neural Stimulation Language Version
• Hopfeild Net with free Java Source
Other Applications

• The tasks artificial neural networks are applied


to tend to fall within the following broad
categories:
• Function approximation, or regression analysis,
including time series prediction, fitness
approximation and modeling.
• Classification, including pattern and sequence
recognition, novelty detection and sequential
decision making.
• Data processing, including filtering, clustering, blind source separation and
compression.
• Robotics, including directing manipulators, Computer numerical control .
• System identification and control (vehicle control, process control)
• Quantum chemistry
• Game-playing and decision making (backgammon, chess, racing)
• Pattern recognition (radar systems, face identification, object recognition
and more)
• Sequence recognition (gesture, speech, handwritten text recognition),
medical diagnosis
• Financial applications (automated trading systems)
• Data mining (or knowledge discovery in databases, "KDD")
• Visualization and e-mail spam filtering.
Overview
• Advantages
– Adapt to unknown situations
– Robustness: fault tolerance due to network
redundancy
– Autonomous learning and generalization

• Disadvantages
– Not exact
– Large complexity of the network structure

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy