From the Publisher:
An Introduction to Nueral Networks will be warmly welcomed by a wide readership seeking an authoritative treatment of this key subject without an intimidating level of mathematics in the presentation.

An introduction to neural networks

Based on a study of the extensive literature in handprint recognition, this paper presents a survey in this challenging field. Recognition algorithms, data bases, character models, and handprint standards are examined. Achievements in the recognition of handprinted numerals, alphanumerics, Fortran, and Katakana characters are analyzed and compared. Data quality and constraints, as well as human and machine factors are also described. Characteristics, problems, and actual results on on-line recognition of handprinted characters for different applications are discussed. New emphases and directions are suggested.

Automatic recognition of handprinted characters&#8212;The state of the art

A cellular logic array for image processing

A masking field network F2, is characterized through systematic computer simulations serves or a content addressable memory. Masking field network F2 receives input patterns from an adaptive filter F1 →F2 that is activated by a prior processing level F1. The network F2 activates compressed recognition close that are predictive with respect to the activation patterns flickering across F1, and competitively inhibits, or masks, codes which are unpredictive with respect to the F1 patterns. The masking field can simultaneously detect multiple groupings within its input patterns and assign activation weights to the recognition codes for these groupings which are predictive with respect to the contextual information embedded within the patterns and the prior learning of the network. Automatic rescaling of sensitivity of the masking field as the overall size of an input pattern changes, allows stronger activation of a code for the whole F1 pattern than for its salient parts. Network F2 also exhibits adaptive sharpening such that repetition of a familiar F1 pattern can tune the adaptive filter to elicit a more focal spatial activation of its F2 recognition code than does an unfamiliar input pattern. The F2 recognition code also becomes less distributed when an input pattern contains more contextual information on which to base an unambiguous prediction of the F1 pattern being processed. Thus the masking field embodies a real-time code to process the predictive evidence contained within its input patterns. Such capabilities are useful in speech recognition, visual object recognition, and cognitive information processin GOVERNMENT SUPPORT This invention was made with Government support under AFOSR-85-0149 awarded by the Air Force. The Government has certain rights in this invention.

Pattern learning and recognition apparatus in a computer system

A self-categorizing pattern recognition system includes an adaptive filter for selecting a category in response to an input pattern A template is then generated in response to the selected category and a coincident pattern indicating the intersection between the expected pattern and the input pattern is generated The ratio between the number of elements and the coincident pattern to the number of elements in the input pattern determines whether the category is reset If the category is not reset, the adaptive filter and template may be modified in response to the coincident pattern Reset of the selected category is inhibited if no expected pattern is generated Weighting of the adaptive filter in response to a coincident pattern is inversely related to the number of elements in the input pattern The selected categories reset where a reset function is less than a vigilance parameter which may be varied in response to teaching events

Pattern recognition system

Pattern feedback is a new concept in learning networks of adaptive microcircuits. The net is trained to produce a model output pattern. During use, the output patterns are fed back to the input. Recognition of an input pattern takes place if a stable model output pattern is generated.

Microcircuit learning nets: improved recognition by means of pattern feedback

A simple transistor circuit suitable for adaptive-logic experiments is described. Its operation depends on the fusing of links in signal pathways, which are selected by subjecting the device to the correct logical operation. Its application to an adaptable two-bit code translator is described.

Fused logic element which learns by example

Networks of adaptive-logic circuits which recognise patterns after being `taught' by an operator have been studied. The letter describes the way in which the performance of such networks may be estimated from a knowledge of the statistical characteristics of the patterns. Results obtained with hand-printed numerals are discussed.

Microcircuit learning nets: some tests with handwritten numerals

The limits of the switching speed of a single-transistor AND gate are discussed. This investigation includes a treatment of a transient `leakage' current condition which can occur in other applications of transistors.

Switching speed of a transistor used as an AND gate

Majority-logic circuits are employed in networks with many stable memory states. Three-state devices are described. The number of states of an N-element memory is calculated and the practical problems associated with large values of N are outlined. A device arising from this work is a decimal memory which uses five transistors.

I. Aleksander

Papers

Microcircuit learning nets: improved recognition by means of pattern feedback

Fused logic element which learns by example

Microcircuit learning nets: some tests with handwritten numerals

Switching speed of a transistor used as an AND gate

Majority-logic memories