Associative processing and processors

Krikelis, A.; Weems, Charles C.

doi:10.1109/2.330035

Cited by 37 publications

(16 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The UPU is mainly characterized by fast, parallel processing based on associative principles [50][51] with an associative memory structure [52]. The main functions of this UPU are problem solving in a high dimensional space and the situational forecasting [14].…”

Section: Future Workmentioning

confidence: 99%

Emotions: The Voice of the Unconscious

Rauterberg

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In the paper the idea is presented that emotions are the result of a high dimensional optimization process happening in the unconscious mapped onto the low dimensional conscious. Instead of framing emotions as a separate subcomponent of our cognitive architecture, we argue for emotions as the main characteristic of the communication between the unconscious and the conscious. We see emotions as the conscious experiences of affect based on complex internal states. Based on this holistic view we recommend a different design and architecture for entertainment robots and other entertainment products with 'emotional' behavior. Intuition is the powerful information processing function of the unconscious while emotion is the result of this process communicated to the conscious. Emotions are the perception of the mapping from the high dimensional problem solving space of the unconscious to the low dimensional space of the conscious.

show abstract

Section: Future Workmentioning

confidence: 99%

Emotions: The Voice of the Unconscious

Rauterberg

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…A decade later, cryogenic elements provided the first viable cell technology for large-scale implementation of associative memories [3]. Further developments in this area are amply documented in various books, article collections, and survey papers [4][5][6][7][8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Extreme-Value Search and General Selection Algorithms for Fully Parallel Associative Memories

Parhami

1996

The Computer Journal

View full text Add to dashboard Cite

Several useful associative memory algorithms deal with identifying extreme values (maximum or minimum) in a specified field of a selected subset of words. Previously proposed algorithms for such extreme-value searches are bit-sequential in nature, even when implemented on fully parallel associative memories. We show how the multiple-bit search capability of a fully parallel associative memory can be used to advantage in reducing the expected search time for finding extreme values. The idea is to search for the all-ones pattern within subfields of the specified search field in lieu of, or prior to, examining bit slices one at a time. Optimal subfield length is determined for both fixed-size and variable-size bit groupings and the corresponding reduction in search time is quantified. The results are extended to rank-based selection where the jth largest or smallest value in a given field of a selected subset of words is to be identified. We conclude that significant reduction in the number of search cycles is possible in most practical extreme-value search and selection problems.

show abstract

“…[8,16]. Many efficient algorithms developed in these areas explore the power of massive associative processing.…”

Section: Introductionmentioning

confidence: 99%