Visual language recognition with a feed-forward network of spiking neurons

Conference · Fri Jan 01 04:00:00 EST 2010

OSTI ID:1024382

Rasmussen, Craig E ^[1]; Garrett, Kenyan ^[1]; Sottile, Matthew ^[2]; Shreyas, Ns ^[3]

---

1. Los Alamos National Laboratory
2. GALOIS
3. INDIANA UNIV.

An analogy is made and exploited between the recognition of visual objects and language parsing. A subset of regular languages is used to define a one-dimensional 'visual' language, in which the words are translational and scale invariant. This allows an exploration of the viewpoint invariant languages that can be solved by a network of concurrent, hierarchically connected processors. A language family is defined that is hierarchically tiling system recognizable (HREC). As inspired by nature, an algorithm is presented that constructs a cellular automaton that recognizes strings from a language in the HREC family. It is demonstrated how a language recognizer can be implemented from the cellular automaton using a feed-forward network of spiking neurons. 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. 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.

• Research Organization: Los Alamos National Laboratory (LANL)
• Sponsoring Organization: DOE
• DOE Contract Number: AC52-06NA25396
• OSTI ID: 1024382
• Report Number(s): LA-UR-10-02784; LA-UR-10-2784
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
ALGORITHMS
COMPUTER ARCHITECTURE
COMPUTERS
INFORMATION SYSTEMS
LEARNING
PARALLEL PROCESSING
PATTERN RECOGNITION