Motivation for neural networks:

• Scientists are challenged to use machines more effectively for tasks currently solved by humans.
• Symbolic Rules don't reflect processes actually used by humans
• Traditional computing excels in many areas, but not in others.

 

 

Types of Applications

 

For machine learning:

• having a computer program itself from a set of examples, so you don't have to program yourself. This will be a strong focus of this course (because it's the most widely successful type of neural network application): neural networks that learn from a set of examples. Whenever you talk about ``training'' a neural network, you're talking about a machine learning setting.
• optimization: given a bunch of constraints and a cost function, how do you find an optimal solution? e.g. house room design. Can be learning- or non-learning based.
• Classification: grouping patterns into classes: i.e. handwritten characters into letters. Usually learning oriented.
• associative memory: recalling a memory based on a partial match.
• regression: function mapping
•  

For cognitive science:

• Modelling higher level reasoning:
  language
  problem solving
• Modelling lower level reasoning:
  vision
  audition speech recognition
  speech generation

 

Neurobiology: Modelling models of how the brain works.

• neuron-level
• higher levels: vision, hearing, etc. Overlaps with cognitive guys.

 

Mathematics:

• Mathematicians also study neural networks in all of these areas, to determine the representational power of this kind of architecture. Nonparametric statistical analysis and regression.

 

For philosophy:

• Can human souls/behavior be explained in terms of symbols, or does it require something lower level, like a neurally based model?

 

Where are neural networks being used?

• Signal processing: suppress line noise, with adaptive echo canceling, blind source separation
• Control: e.g. backing up a truck: cab position, rear position, and match with the dock get converted to steering instructions.
• Siemens successfully uses neural networks for process automation in basic industries, e.g., in rolling mill control more than 100 neural networks do their job, 24 hours a day
• Robotics - navigation, vision recognition
• Pattern recognition, i.e. recognizing handwritten characters, e.g. the current version of Apple's Newton uses a neural net
• Medicine, i.e. storing medical records based on case information
• Speech production: reading text aloud (NETtalk)
• Speech recognition
• Vision: face recognition , edge detection, visual search engines
• Business,e.g.. rules for mortgage decisions are extracted from past decisions made by experienced evaluators, resulting in a network that has a high level of agreement with human experts.
• Financial Applications: time series analysis, stock market prediction
• Data Compression: speech signal, image, e.g. faces
• Game Playing: backgammon
• etc...