NNW Applications
in General
 
  • NNW's, despite all appearances to the contrary, are appearing in ever increasing numbers of real world applications and are making real money:

  •  
    • OCR (Optical Character Recognition)
      • Caere Inc ($3M profit on $55M revenue in 1997) "OmniPage Pro 6.0 significantly increases accuracy with its exclusive Quadratic Neural Network(TM) (QNN) technology, an enhancement to its industry-leading OCR engine..."

      •  
    • Data Mining
      • HNC ($23M profit on $110M revenue in 1997). Their flagship product is Falcon. "Falcon is a neural network-based system that examines transaction, cardholder, and merchant data to detect a wide range of credit card fraud...". 
     
  • These days a purchase of a new scanner typically includes a commercial OCR program.

  •  
  • The algorithms used are proprietary but most OCR programs are believed to use NNWs. (Calera, started in 1986, did not admit to using NNW in its OCR programs until 1992 when Caere began advertising the use of them in its OCR products).
  •  

  • However, the OCR example also illustrates why one cannot claim NNWs are conquering the world.

  •  
  • One does not feed the pixels of the picture file into a single giant NNW and out pops the text.

  •  
  • To turn a picture of text into a text file, a dozen or more steps must be completed successfully by the OCR program. For example, an OCR system might follow the step in the diagram:

  •  
From Adaptive Solutions CNAPS user guide.
       
       
  • Designers of OCR programs may choose NNWs to accomplish one or more of these steps with NNWs while using for other steps other techniques such as conventional AI (If-Then rules), statistical models, hidden Markov models, etc.

  •  
  • The point is that NNWs are becoming commonly used tools but, just like other math techniques such as FFT and least squares fit, they are still only tools, not the whole solution.

  •  
  • Few real problems of interest can be totally solved by a single NNW. 
Lecture 1:
NNW Applications
24-2-98