CLICK HERE TO DOWNLOAD PPT ON Artificial Neural Networks
Artificial Neural Networks Presentation Transcript
1.Artificial Neural Networks
2.Overview
Introduction
Biological inspiration
Artificial neurons and neural networks
Learning processes
Learning with artificial neural networks
Introduction
Biological inspiration
Artificial neurons and neural networks
Learning processes
Learning with artificial neural networks
3.Introduction
What is an (artificial) neural network
A set of nodes (units, neurons, processing elements)
Each node has input and output
Each node performs a simple computation by its node function
Weighted connections between nodes called Synaptic Weight.
Connectivity gives the structure/architecture of the net
What can be computed by a NN is primarily determined by the connections and their weights
A very much simplified version of networks of neurons in animal nerve systems
What is an (artificial) neural network
A set of nodes (units, neurons, processing elements)
Each node has input and output
Each node performs a simple computation by its node function
Weighted connections between nodes called Synaptic Weight.
Connectivity gives the structure/architecture of the net
What can be computed by a NN is primarily determined by the connections and their weights
A very much simplified version of networks of neurons in animal nerve systems
4.STRUCTURE OF NEURON
Each neuron has a body, an axon, and many dendrites
Can be in one of the two states: firing and rest.
Neuron fires if the total incoming stimulus exceeds the threshold
Synapse: thin gap between axon of one neuron and dendrite of another.
Signal exchange
Synaptic strength/efficiency
Each neuron has a body, an axon, and many dendrites
Can be in one of the two states: firing and rest.
Neuron fires if the total incoming stimulus exceeds the threshold
Synapse: thin gap between axon of one neuron and dendrite of another.
Signal exchange
Synaptic strength/efficiency
5.Structure of Neuron
6.COMPARISON
7.Neural Network Architecture
Single Layer Feed forward Network
Multi Layer Feed forward Network
Recurrent Network
Single Layer Feed forward Network
Multi Layer Feed forward Network
Recurrent Network
8.Single Layer Feed forward Network
Input Layer of source node that projects on to an output layer of nuerons(computation nodes) but not vice-versa.
This is refers as a single layer network because processing or computation takes place only on output layer.
Input Layer of source node that projects on to an output layer of nuerons(computation nodes) but not vice-versa.
This is refers as a single layer network because processing or computation takes place only on output layer.
9.Multi Layer Feed Forward Network
10.Recurrent Network
At least one feedback loop.
Consist of a single layer of neurons.
Each neuron feeding its output signal back as inputs of others neurons except itself.
May or may not have Hidden neurons.
At least one feedback loop.
Consist of a single layer of neurons.
Each neuron feeding its output signal back as inputs of others neurons except itself.
May or may not have Hidden neurons.
11.Biological inspiration
Animals are able to react adaptively to changes in their external and internal environment, and they use their nervous system to perform these behaviours.
An appropriate model/simulation of the nervous system should be able to produce similar responses and behaviours in artificial systems.
The nervous system is build by relatively simple units, the neurons, so copying their behavior and functionality should be the solution.
Animals are able to react adaptively to changes in their external and internal environment, and they use their nervous system to perform these behaviours.
An appropriate model/simulation of the nervous system should be able to produce similar responses and behaviours in artificial systems.
The nervous system is build by relatively simple units, the neurons, so copying their behavior and functionality should be the solution.
12.The information transmission happens at the synapses.
13.Biological inspiration
The spikes travelling along the axon of the pre-synaptic neuron trigger the release of neurotransmitter substances at the synapse.
The neurotransmitters cause excitation or inhibition in the dendrite of the post-synaptic neuron.
The integration of the excitatory and inhibitory signals may produce spikes in the post-synaptic neuron.
The contribution of the signals depends on the strength of the synaptic connection.
The spikes travelling along the axon of the pre-synaptic neuron trigger the release of neurotransmitter substances at the synapse.
The neurotransmitters cause excitation or inhibition in the dendrite of the post-synaptic neuron.
The integration of the excitatory and inhibitory signals may produce spikes in the post-synaptic neuron.
The contribution of the signals depends on the strength of the synaptic connection.
14.Artificial neural networks
An artificial neural network is composed of many artificial neurons that are linked together according to a specific network architecture. The objective of the neural network is to transform the inputs into meaningful outputs.
An artificial neural network is composed of many artificial neurons that are linked together according to a specific network architecture. The objective of the neural network is to transform the inputs into meaningful outputs.
15.Tasks to be solved by artificial neural networks:
controlling the movements of a robot based on self-perception and other information (e.g., visual information);
deciding the category of potential food items (e.g., edible or non-edible) in an artificial world;
recognizing a visual object (e.g., a familiar face);
predicting where a moving object goes, when a robot wants to catch it.
controlling the movements of a robot based on self-perception and other information (e.g., visual information);
deciding the category of potential food items (e.g., edible or non-edible) in an artificial world;
recognizing a visual object (e.g., a familiar face);
predicting where a moving object goes, when a robot wants to catch it.
16.ANN Business Applications
Evaluation of personnel and job candidates
Resource allocation
Data mining
Foreign exchange rate
Stock, bond, and commodities selection and trading
Signature validation
Tax fraud
Loan applications evaluation
Solvency prediction
New product analysis
Airline fare management
Prediction
Evaluation of personnel and job candidates
Resource allocation
Data mining
Foreign exchange rate
Stock, bond, and commodities selection and trading
Signature validation
Tax fraud
Loan applications evaluation
Solvency prediction
New product analysis
Airline fare management
Prediction
Posts
0 comments