The text processor, called ALTEP (associative linear text processor), is a linear array of logic moreВ В» cells capable of matching regular expressions at a much higher speed than that of previous designs. The signature processor is based on a word-parallel, bit-serial (WPBS) organization which is faster, more efficient, and more flexible than a word-serial, bit-parallel (WSBP) organization proposed in the literature. HYTREM consists of two major subsystems: a signature processor and a text processor. A signature file is used as an access method to reduce the amount of data that need to be searched directly. This paper describes the design of a text-retrieval machine, called HYTREM (hybrid text-retrieval machine), for the support of large unformatted text databases. The analogy with formal language theory allows inferences to be drawn regarding what class of objects can be recognized by visual cortex operating in purely feed-forward fashion and what class of objects requires a more complicated network architecture. This parser recognizes fixed-length strings from the language in parallel and as the computation is pipelined, a new string can be parsed in each new interval of time. It is demonstrated how a language recognizer moreВ В» can be implemented from the cellular automaton using a feed-forward network of spiking neurons. As inspired by nature, an algorithm is presented that constructs a cellular automaton that recognizes strings from a language in the HREC family.

A language family is defined that is hierarchically tiling system recognizable (HREC). This allows an exploration of the viewpoint invariant languages that can be solved by a network of concurrent, hierarchically connected processors. A subset of regular languages is used to define a one-dimensional 'visual' language, in which the words are translational and scale invariant. = ,ДЄn analogy is made and exploited between the recognition of visual objects and language parsing.

Finite state automata to regex