Applying Standards to Neural Networks

Harry Erwin erwin at trwacs.fp.trw.com
Fri Feb 12 11:54:57 EST 1993


I was asked to review a proposal concerning the standardization of
vocabulary for machine learning and neural networks. This is being
distributed by the U.S. Technical Advisory Group to ANSI (JTC1 TAG). X3K5
is coordinating and developing a recommended position to JTC1 TAG for
approval for submission to ISO/IEC JTC 1. This recommendation has to be
returned to the JTC1 TAG Administrator no later than 1 March, 1993. The
contact person is the
  JTC1 TAG Administrator
  Computer and Business Equipment Manufacturers Association (CBEMA)
  1250 Eys Street NW, Suite 200
  Washington, DC 20005-3922
  phone: 202-737-8888 (Press 1 Twice)

The vocabulary whose definitions are being standardized include:

 "knowledge acquisition"
 "learning strategy"
 "concept"
 "concept learning"
 "conceptual clustering"
 "taxonomy formation"
 "machine discovery"
 "connectionist model"
 "massively parallel processing"
 "connection machine"
 "connection system"
 "neural network"
 "connectionist network"
 "neurocomputer"
 "learning task"
 "concept description"
 "chunking"
 "discrimination network"
 "characteristic description"
 "discriminant description"
 "structural description"
 "concept formation"
 "partially learned concept"
 "version space (of a concept)"
 "description space"
 "instance space (of a concept)"
 "(concept) generalization"
 "consistent generalization"
 "constraint-based generalization"
 "similarity-based generalization"
 "complete generalization"
 "specialization"
 "caching (in machine learning)"
 "concept validation"
 "confusion matrix"
 "rote learning"
 "adaptive learning"
 "advice taking"
 "learning by being told"
 "learning from instruction"
 "incremental learning"
 "supervised learning"
 "inductive learning"
 "learning from induction"
 "deductive learning"
 "analytic learning"
 "explanation-based learning"
 "operationalization"
 "learning by analogy"
 "associative learning"
 "learning from observation and discovery"
 "learning without a teacher"
 "unsupervised learning"
 "learning from examples"
 "positive example"
 "negative example"
 "near-miss"
 "credit/blame assignment"
 "causal analysis"
 "unit (in neural networks)"
 "link (in neural networks)"
 "stable coalition"
 "hidden layer"
 "back propagation"
 "transfer function"

For example, a "neural network" or "connectionist network" is defined as a
"A network of neuron-like processors each of which performs some simple
logical function, typically a logic threshold function. NOTE A neural
network completes a computation when its units have finished exchanging
messages and updating their potential, and settle into a stable state."

A "hidden layer" is defined as "An object-oriented software layer which
contains the method of instruction delivery among different programs run
by different types of data. NOTE Every processor is told to block out any
program that does not apply to the data object stored in it. From the
user's point of view however it appears that different types of processors
run different programs."

--My recommendation on this proposal to the TRW representative to this
standardization body is to vote no, since it is highly premature to
standardize on terminology when the underlying concepts remain the subject
of such active research."

Cheers,
-- 
Harry Erwin
Internet: erwin at trwacs.fp.trw.com



More information about the Neur-sci mailing list