Академический Документы
Профессиональный Документы
Культура Документы
Mansoura University
Faculty of Computers & Information Sciences
Department of Information Systems
elmogy@gmail.com
5. October 2011
Outline
Introduction
Natural and Artificial Neurons
ANN Learning
ANNs Types
Where are NN Used?
Outline
Introduction
Natural and Artificial Neurons
ANN Learning
ANNs Types
Where are NN Used?
What are computer systems good at... and not so good at?
Outline
Introduction
Natural and Artificial Neurons
ANN Learning
ANNs Types
Where are NN Used?
Artificial Neurons
I The neuron calculates a weighted sum of inputs and compares
it to a threshold. If the sum is higher than the threshold, the
output is set to 1, otherwise to 0.
A Simple Perceptron
Outline
Introduction
Natural and Artificial Neurons
ANN Learning
ANNs Types
Where are NN Used?
Learning
I From experience: examples / training data.
Operation Mode
I Fix weights (unless in online learning).
I Inherently parallel.
Evolving Networks
I Continuous process of:
I Evaluate output.
I Adapt weights.
I Take new inputs.
Outline
Introduction
Natural and Artificial Neurons
ANN Learning
ANNs Types
Where are NN Used?
Learning Performance
I Network architecture.
I Learning method: Unsupervised, Reinforcement learning, and
Backpropagation.
Unsupervised Learning
I No help from the outside.
I No training data, no information available on the desired
output.
I Learning by doing.
I Used to pick out structure in the input:
I Clustering
I Reduction of dimensionality =⇒ compression
I Example: Kohonen’s Learning Law.
SOM
SOM (cont.)
Reinforcement Learning
I Teacher: training data.
Back Propagation
I It is a supervised learning method. It requires a teacher that
knows, or can calculate, the desired output for any input in the
training set.
Online / Offline
I Offline
I Weights fixed in operation mode.
I Most common.
I Online
I System learns while in operation mode.
I Requires a more complex network architecture.
Outline
Introduction
Natural and Artificial Neurons
ANN Learning
ANNs Types
Where are NN Used?
I Data is unreliable.
General Advantages
I Advantages:
I Adapt to unknown situations.
I Robustness: fault tolerance due to network redundancy.
I Autonomous learning and generalization.
I Disadvantages:
I Not exact.
I Large complexity of the network structure.