Download Neural Networks - Temple Fox MIS

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Neuroesthetics wikipedia , lookup

Neuroethology wikipedia , lookup

Cortical cooling wikipedia , lookup

Neuroeconomics wikipedia , lookup

Artificial general intelligence wikipedia , lookup

Neurocomputational speech processing wikipedia , lookup

Neural coding wikipedia , lookup

Holonomic brain theory wikipedia , lookup

Neural oscillation wikipedia , lookup

Synaptic gating wikipedia , lookup

Neural modeling fields wikipedia , lookup

Optogenetics wikipedia , lookup

Biological neuron model wikipedia , lookup

Channelrhodopsin wikipedia , lookup

Gene expression programming wikipedia , lookup

History of artificial intelligence wikipedia , lookup

Neuropsychopharmacology wikipedia , lookup

Central pattern generator wikipedia , lookup

Artificial intelligence wikipedia , lookup

Pattern recognition wikipedia , lookup

Metastability in the brain wikipedia , lookup

Nervous system network models wikipedia , lookup

Development of the nervous system wikipedia , lookup

Neural engineering wikipedia , lookup

Catastrophic interference wikipedia , lookup

Artificial neural network wikipedia , lookup

Convolutional neural network wikipedia , lookup

Recurrent neural network wikipedia , lookup

Types of artificial neural networks wikipedia , lookup

Transcript
Neural Networks
Week 5
Applications

Predict the taste of Coors beer as a function of its
chemical composition
What are Artificial Neural
Networks?

Artificial Intelligence (AI) Technique

Artificial Neural Networks (ANN) are biologically
inspired and attempt to build computer models that
operate like a human brain

These networks can “learn” from the data and recognize
patterns
Basic Concepts
of Neural Networks

Biological and artificial neural networks

Neurons
Cells (processing elements) of a biological or artificial neural network

Nucleus
The central processing portion of a neuron

Dendrite
The part of a biological neuron that provides inputs to the cell
Basic Concepts
of Neural Networks

Biological and artificial neural networks

Axon
An outgoing connection (i.e., terminal) from a biological neuron

Synapse
The connection (where the weights are) between processing elements in a neural
network
Basic Concepts
of Neural Networks
Basic Concepts
of Neural Networks
Relationship Between
Biological and Artificial
Neural Networks

Soma – Node

Dendrites – Input

Axon – Output

ANNs typically have much fewer neurons than humans
Basic Concepts
of Neural Networks

Network structure (three layers)

Input

Intermediate (hidden layer)

Output
Basic Concepts
of Neural Networks
Basic Concepts
of Neural Networks

Transformation function (activation function)




maps the summation (combination) function onto a
narrower range ( 0 to 1 or -1 to 1) to determine whether
or not an output is produced (neuron fires)
The transformation occurs before the output reaches the
next level in the network
Sigmoid (logical activation) function: an S-shaped
transfer function in the range of zero to one –exp(x)/(1exp(x))
Threshold value is sometimes used instead of a
transformation function

A hurdle value for the output of a neuron to trigger the
next level of neurons. If an output value is smaller than
the threshold value, it will not be passed to the next
level of neurons
Neural Network Prediction Formula
hidden unit
prediction
estimate
bias
estimate
weight
estimate
1
tanh
-5
0
-1
5
activation
function
...
Neural Network Binary Prediction Formula
5
logit
link function
1
tanh
-50
0
-5
-1
15
...
Learning in ANN

Learning algorithm
The training procedure used by an artificial neural network

Supervised learning
A method of training artificial neural networks in which sample cases are shown
to the network as input and the weights are adjusted to minimize the error in its
outputs
Learning in ANN
Learning in ANN
How a network learns


Backpropagation
The best-known supervised learning algorithm in neural computing. Learning is
done by comparing computed outputs to desired outputs of historical cases
Learning in ANN
How a network learns


Procedure for a learning algorithm
1.
Initialize weights with random values and set other parameters
2.
Read in the input vector and the desired output
3.
Compute the actual output via the calculations, working forward through the layers
4.
Compute the error
5.
Change the weights by working backward from the output layer through the hidden
layers
Learning in ANN
Error calculation and weights

At each hidden node and target node: compute:
Linear combination function: C = w0 + w1x1 +…+ wnxn
Logistic activation function: L = exp(C)/(1+exp(C)

At the target node compute Bernoulli error function: sum errors
over all observations, where the error is -2 ln (L) if there is a
response, or -2 ln (1 – L) if there is no response

In the first iteration, random weights are used

In subsequent iterations, the weights are changed by a small
amount so that the error is reduced

The process continues until the weights cannot be reduced further
Classification using NN
training p.
prerequisite

set of training pattern (many patterns)
coded p.
approach

code the values

divide set of training pattern into:
–
–
training set
training set
test set

build a network

train the network using the training set

check the network quality using the test set
real data
test set
Business Applications of
Artificial Neural Networks
(ANN)

Many applications across all areas of business









target customers (CRM)
bank loan approval
hiring
stock purchase
trading electricity
approving loan applications
fraud prevention
predicting bankruptcy
time series forecasting
Disadvantages of Neural
Networks

coefficients are not readily interpretable

end user must apply insight in interpretation

Questions!