Artificial Intelligence (AI)

1
Artificial Intelligence (AI)

• Addition to the lecture 11

2
What is AI?

• It is the science and engineering of making
  intelligent machines, especially intelligent
  computer programs. It is related to the similar
  task of using computers to understand human
  intelligence, but AI does not have to confine
  itself to methods that are biologically
  observable
• Applications of AI
• game playing
• speech recognition
• understanding natural language
• computer vision
• expert systems
• heuristic classification

http//www-formal.stanford.edu/jmc/whatisai/node3.
html
3
Knowledge-based expert system

• Artificial neural network (ANN)
• Decision tree
• Support vector machines (SVMs)

4
Knowledge representation process
The knowledge representation process normally
involves encoding information from verbal
descriptions, rules of thumb, images, books,
maps, charts, tables, graphs, equations, etc.
Hopefully, the knowledge base contains sufficient
high-quality rules to solve the problem under
investigation. Rules are normally expressed in
the form of one or more IF condition THEN
action statements. The condition portion of a
rule statement is usually a fact, e.g., the pixel
under investigation must reflect gt 45 of the
incident near-infrared energy. When certain rules
are applied, various operations may take place
such as adding a newly derived derivative fact to
the database or firing another rule. Rules can be
implicit (slope is high) or explicit (e.g., slope
gt 70). It is possible to chain together rules,
e.g., IF c THEN d IF d THEN e therefore IF c
THEN e. It is also possible to attach confidences
(e.g., 80 confident) to facts and rules.
5
For example, a typical rule used by the MYCIN
expert system is IF the stain of the organism is
gram-negative     AND the morphology of the
organism is rod         AND the aerobicity of
the organism is anaerobic             THEN there
is strong suggestive evidence (0.8) that the
class of the organism is Enterobacter iaceae.
Following the same format, a typical remote
sensing rule might be IF blue reflectance is
(Condition) lt 15     AND green
reflectance is (Condition) lt 25 AND
red reflectance is (Condition) lt 15
AND near-infrared reflectance is (Condition) gt
45 THEN there is strong
suggestive evidence (0.8) that the
pixel is vegetated.
6
1. ANN

• The motivation for the development of neural
  network technology stemmed from the desire to
  develop an artificial system that could perform
  "intelligent" tasks similar to those performed by
  the human brain (thousands of different
  inputs-neurons, output to many other neurons),
  with
• Simple processing elements
• A high degree of interconnection
• Simple scalar messages
• Adaptive interaction between elements
• ANN usually has one input layer, one output
  layer, and no or some hidden layers between.
  Neurons in one layer are connected to all neurons
  in the next layer for passing information
• Neural networks process information in a similar
  way the human brain does. The network is composed
  of a large number of highly interconnected
  processing elements (neurones) working in
  parallel to solve a specific problem. Neural
  networks learn by example. They cannot be
  programmed to perform a specific task. The
  examples must be selected carefully otherwise
  useful time is wasted or even worse the network
  might be functioning incorrectly. The
  disadvantage is that because the network finds
  out how to solve the problem by itself, its
  operation can be unpredictable.

7
How do ANN work?

• Train the Network
• Input training sites to the network
• Network computes an output
• Network output compared to desired output
• Network weights are modified to reduce error
• Use the network
• Input new data to the network
• Network computes outputs based on its training

8
An example of a complicated ANN
9
2. Decision tree

• "A decision tree takes as input an object or
  situation described by a set of properties, and
  outputs a yes/no decision. Decision trees
  therefore represent Boolean functions. Functions
  with a larger range of outputs can also be
  represented...."

10
Cont

• A decision tree is a type of multistage
  classifier that can be applied to a single image
  or a stack of images. It is made up of a series
  of binary decisions that are used to determine
  the correct category for each pixel. The
  decisions can be based on any available
  characteristic of the dataset. For example, you
  may have an elevation image and two different
  multispectral images collected at different
  times, and any of those images can contribute to
  decisions within the same tree. No single
  decision in the tree performs the complete
  segmentation of the image into classes. Instead,
  each decision divides the data into one of two
  possible classes or groups of classes.
• Image segmentation (eCognition)
• decision tree (such as see5 at
  http//www.rulequest.com/see5-info.html)

11
Hierarchical Decision Tree Classifier
ETM Panchromatic
Experts Model
Predicted White Fir
12
Hierarchical Decision Tree Classifier Based on
Inductive Machine Learning Production Rules
ETM Panchromatic
C5.0 Model
Predicted White Fir
13
Machine Learning-derived Classification Map
14
Thomas, et al. 2003, PERS
15
(No Transcript)
16
Cont

• ENVIs decision tree tool is designed to
  implement decision rules, such as the rules
  derived by any number of excellent statistical
  software packages that provide powerful and
  flexible decision tree generators. Two examples
  that are used commonly in the remote sensing
  community include CART by Salford Systems and
  S-PLUS by Insightful. The logic contained in the
  decision rules derived by these software packages
  can be used to build a decision tree classifier
  with ENVIs interactive decision tree tool.
• Even if you have not used one of these packages
  to derive any decision rules, you may find ENVIs
  new decision tree tool to be a useful way to
  explore your data, or to find areas in your data
  that fulfill certain criteria.

17
3. Support vector machines (SVMs)

• Is a new generation learning system based on
  recent advances in statistical learning theory
• SVMs deliver state-of-the-art performance in
  real-world applications such as text
  categorisation, hand-written character
  recognition, image classification, biosequences
  analysis, etc.
• SVMss first introduction in the early 1990s lead
  to a recent explosion of applications and
  deepening theoretical analysis, that has now
  established SVMs along with neural networks as
  one of the standard tools for machine learning
  and data mining

18
Want to learn more?

• http//svmlight.joachims.org/
• http//svm.dcs.rhbnc.ac.uk/
• http//www.csie.ntu.edu.tw/cjlin/libsvm/
• http//theoval.sys.uea.ac.uk/gcc/svm/toolbox/
• http//www.cs.wisc.edu/dmi/lsvm/
• http//vision.ai.uiuc.edu/mhyang/svm.html