A hardware implementation of a binary neural image processor

The paper presents the work that has resulted in the sum and threshhold (SAT) processor; a dedicated hardware implementation of a binary neural image processor. The SAT processor is aimed specifically at supporting the ADAM algorithm and is currently being integrated into a new version of the C-NNAP...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kennedy, J.V, Austin, J, Cass, B
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Computer vision and image processing techniques Digital signal processing chips Microprocessors and microcomputers Neural computing techniques Neural nets (circuit implementations) Optical information, image and video signal processing Parallel architecture Pattern recognition and computer vision equipment Semiconductor integrated circuits
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The paper presents the work that has resulted in the sum and threshhold (SAT) processor; a dedicated hardware implementation of a binary neural image processor. The SAT processor is aimed specifically at supporting the ADAM algorithm and is currently being integrated into a new version of the C-NNAP parallel image processor. The SAT processor performs binary matrix multiplications, a task that is computationally complex for a CPU with a standard instruction set. It can perform the matrix multiplication and thresholding between 100 and 200 times faster than the DSP32C that uses an in-house produced dedicated coprocessor. This speed-up will allow the SAT to process images of up to 220×220 pixels at 25-Hz frame rates.
DOI:	10.1049/cp:19950702