Lecture 7 () - ANN - Faculty of Computer Science and
Transcript Lecture 7 () - ANN - Faculty of Computer Science and
Artificial Neural Networks (ANNs)
ABC Enterprise, as a multinational company has
invested in many country sectors for revenues
generation. One of the potential revenue for the
company comes from the investment in the BSKL
shares. The CEO of the company, Mr. Ridzuan intends
to invest in selected potential shares available in the
current market. He is aware that such investment is a
risky business. Unfortunately, he does not have
experienced staff to advice on the potential shares
investment. Thus, Mr. Ridzuan is thinking whether
there is any system that can predict short and long
term future of current shares trading in the market
with accurately. The system must be able to analyze
history of the current shares trading and predicts
when the best time to buy the shares is.
50 to 150 billion neurons in brain (estimation)
Neurons grouped into networks
Axons send outputs to cells
Received by dendrites, across synapses
Artificial Neural Networks (ANNs)
A model that emulates a biological neural
Software simulations of the massively parallel
processes that involve processing elements
interconnected in a network architecture.
Originally proposed as a model of the human
The human brain is much more complex.
in an Artificial Neuron
Σ wij xi
Processing elements are neurons
Allows for parallel processing
Each input is single attribute
Adjustable mathematical value of input
Weighted sum of input elements
Relation between internal activation and output
Outputs are problem solution
Learning: Three Tasks
The neurons are connected by links, and each
link has a numerical weight associated with it.
Weights are the basic means of long term
memory in ANN. They express the strength or
importance of each neuron input. ANN learns
through repeated adjustments of these
weights. In summary, learning in ANN
involves three tasks:
1. Compute Outputs
2. Compare Outputs with Desired Targets
3. Adjust Weights and Repeat the Process
Learning is a fundamental characteristic
Two Basic Learning Categories
For a set of inputs with known (desired) outputs.
Connection weights derived from known cases.
Useful in pattern recognition (character, voice,
Supervised Learning : Character Recognition
Demonstration of a neural network used within an optical character recognition (OCR) application. The
original document is scanned into the computer and saved as an image. The OCR software breaks the
image into sub-images, each containing a single character. The sub-images are then translated from an
image format into a binary format, where each 0 and 1 represents an individual pixel of the sub-image.
The binary data is then fed into a neural network that has been trained to make the association between
the character image data and a numeric value that corresponds to the character. The output from the
neural network is then translated into ASCII text and saved as a file.
Only input stimuli shown to the network.
Humans assign meanings and determine
Useful in clustering (objects) and knowledge
Adaptive Resonance Theory (ART)
Kohonen Self-organizing Feature Maps
Unsupervised Learning :
Classification of raw data into two subgroups.
Development of Systems
Separate data into training set to adjust weights
Divide into test sets for network validation
Select network topology
The more, the better
Determine input, output, and hidden nodes, and hidden
Select learning algorithm and connection weights
Iterative training until network achieves preset error
Black box testing to verify inputs produce appropriate
Contains routine and problematic cases
Neural Network Software
Tools (shells) incorporate: (MATLAB)
Programming language (C++, Java, VB)
Neural network package or NN programming tool
Transfer and summation functions
May still need to:
Program the layout of the database
Partition the data (test data, training data)
Transfer the data to files suitable for input to an ANN
Advantages of ANNs
Pattern recognition, classification,
generalization, interpretation of incomplete
and noisy inputs.
Character, speech and visual recognition.
Can tackle new kinds of problems.
Robust, flexible and easy to maintain.
Powerful hybrid systems.
Limitations of ANNs
Do not do well at tasks that are not done well by
Lack explanation capabilities
Limitations and expense of hardware technology
restrict most applications to software simulations
Training time can be excessive and tedious
Usually requires large amounts of training and test
NeuroXL Classifier (add-in for Ms Excell)
N-OCR (character recognition)
Neural Network Toolbox (MathWorks)
Intelligence Density Dimension
Independence from experts