Artificial Neural Networks ??????? ??????? ??????????

1
Artificial Neural Networks ??????? ???????
??????????
2
What is a Neural Network?

• An artificial neural network (ANN) is an
  information-processing system that has certain
  performance characteristics in common with
  biological neural networks.
• ?????? ??????? ?????????? ?? ????? ?? ????
  ??????? ???????? ???? ????? ? ????? ??????? ????
  ???? ??? ??????? ??????? ????????
• A method of computing, based on the interaction
  of multiple connected processing elements.
• ????? ???????? ????? ??? ????? ????? ????????
  ???????? ????????
• mathematical models for information processing,
  which based on the biological prototypes and
  mechanisms of human brain activities.
• ??????? ???????? ??????? ????????? ????? ???
  ??????? ???????? ????? ???? ???? ??????? .

3

• Computational models inspired by the human brain
• ??????? ???????? ??????? ?? ????? ??????
• Massively parallel, distributed system, made up
  of simple processing units (neurons)
• ?????? ?????? ???????? ???? ?? ????? ?????? ?????
  (??????? )
• Synaptic connection strengths among neurons are
  used to store the acquired knowledge.
• ??? ??????? ??????? ??? ??????? ??????? ??????
  ?????? ??????? ????????
• Knowledge is acquired by the network from its
  environment through a learning process
• ??????? ????? ?? ?????? ?? ?????? ?? ???? ?????
  ???????

4
History of Neural Networks????? ??????? ???????

• 1943 McCullough and Pitts - Modeling the Neuron
  for Parallel Distributed Processing
• 1958 Rosenblatt - Perceptron
• 1969 Minsky and Papert publish limits on the
  ability of a perceptron to generalize
• 1970s and 1980s ANN renaissance??? ????
  ??????? ??????? ??????????
• 1986 Rumelhart, Hinton Williams present
  backpropagation
• 1989 Tsividis Neural Network on a chip

5
Properties of Nervous Systems????? ???????
???????

• Parallel, distributed information processing
• ?????? ??????? ????? ????????
• High degree of connectivity among basic units
• ???? ????? ????? ??? ??????? ????????
• Connections are modifiable based on experience
• ????????? ??????????? ???? ??????? ??? ???????
• Learning is a constant process, and usually
  unsupervised
• ??????? ?? ????? ????? ????? ??? ???? ?????
• Learning is based only on local information
• ??????? ????? ??? ??? ????????? ???????

6
Biological Neuron

• The basic computational unit in the nervous
  system is the nerve cell, or neuron. A neuron
  has
• Dendrites (inputs) ??????? ?????? ??????? ??
  ??????? ??????? ??????
• Cell body ??? ???? ??? ?????? ? ?? ???? ??? ?????
  ???????? ????????? ?? dendrites
• Axon (output) ???? ??????? ??? ?????? ???????

7
(No Transcript)
8
Model of an artificial neuron
9
Model of an artificial neuronTerminology(????????
? )

• x1, x2, ...., xn are the inputs to the neuron
• w1, w2, ...., wn are real-valued parameters
  called weights
• net w1 x1 w2 x2 wn xn is called the
  weighted sum
• f is called the activation function?(????
  ??????? )
• y f(net) is the output of the neuron

10
Model of an artificial neuron
11
Network Architecture

• Single layer net

Single layer network
Input Output layer
layer
12
Multi-layer net
x1
x2
Input
Output
xn
Hidden layers
13
Feed-forward nets????? ??????? ????????

• Information only flows one way
• ????????? ??? ???? ???? ????
• Data is presented to Input layer
• ???????? ???? ????? ?????
• Passed on to Hidden Layer
• ???? ??? ?????? ???????
• Passed on to Output layer
• ???? ????? ?????
• Information is distributed
• ????????? ?????
• Information processing is parallel
• ?????? ????????? ???? ???? ??????

Internal representation (interpretation) of
data ??????? ??????? ?? ????? ????????
14
Recurrent Networks??????? ????????

• Nodes connect back to other nodes or themselves.
• Information flow is multidirectional
• ????? ???? ?????? ?? ???? ????
• ???? ????????? ????? ?????????

15
Learning Algorithm???????? ???????

• Supervised Learning
• Unsupervised Learning

15
16
Common Activation Functions
Identity Function
The identity function is given by
17

• Binary step function
• Threshold activation function

Stepf(x) 1 if x gt Ø, else 0
18
Binary sigmoid function
19
Applications of Artificial Neural Networks

• Signal processing(?????? ??????? )
• ??? ????? ????? ?? ???? ???????
• ????? ?????
• Control(?????? )
• ??? ?????? ?? ???????? ??? ????? ???? ????? ????
  
• Robotics - navigation, vision recognition
• ??????? ????? ??????? ????? ??????
• Pattern recognition.
• ?????? ??? ??????? ??? ??????? ??????? ?? ?????
  ?? ???? ???? ?? ???????

20

• Medicine. (????)
• ????? ??????? ?????? ????????? ??? ??????? ??????
• Speech production. (????? ??????? )
• Speech recognition. ?????? ??? ???????) )
• Vision face recognition , visual search engines
• ????? ?????? ???? ??? ?????
• Business.(??????? )
• ???? ????? ??????? ????????
• Financial Applications time series analysis,
  stock market prediction
• ????????? ??????? ????? ??????? ??????? ????
  ??? ?????? ???????
• Data Compression image, e.g. faces
• ??? ???????? ????? ???????
• Game Playing backgammon, chess, go, ...
• ??????? ???????? ????? ???????

21
Applications of Artificial Neural Networks
Intelligent Control
?????? ?????
AdvanceRobotics
Technical Diagnistics
Intelligent Data Analysis and Signal Processing
??????? ??????? ??????
Image Pattern Recognition
??????? ??????? ??????
Intelligent Expert Systems
Intelligent Security Systems
Intelligentl Medicine Devices
21