Adaptive segmentation of quantizer neuron architecture (ASQA)

Maruno, S.; Imagawa, Taro; Kohda, Takehisa; Kojima, Yoshiyuki; Yamamoto, Hiroyuki; Shimeki, Y.

doi:10.1109/ijcnn.1993.713933

Cited by 4 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ASQA chip call execute Kanji characters (2:96S categories) recognition with only a single chip aiid three 10 Mh DRAMS. I11 this paper, we will present the principle 01' a proposed prolilerating neuron iiiodel [4], "Adaptive Segmentation Quantizer iieuroii Archilecturc : ASQA". aiid a iiiulti NN model IS], "Neural networks designed 011 Approximate Reasoning Architecture : NARA".…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A digital neuro chip with adaptive segmentation quantizer neuron architecture (ASQA)

Fukuda¹,

Nakahira²,

Sakiyama³

et al.

Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop

Self Cite

View full text Add to dashboard Cite

bstract In this paper, we discuss a chip simulates a neural network. and titomatically generates optiinuin iietwork stnicture according to input data. It handles 28 sub ne~ual networks which coinpose a large scale neural network. By our origiiial rchitecture, iiecessary inernory size to get the same recognition performancc as nnventional chip is reduced to 9%. It classilks up to 16,384 categories and solvcs lrge size prohleins such as Kaiiji recognition oii a single chip. It consists (IC 250K aiisistors on a 6.02 i i i~i i x 7.08 iiiiii chip by 0.5 pili douhle iiictal CMOS tcchnology. . INTRODUCTIONBoth digital aiid analog iieuro chips have been iinpleineiited for a purpose of high )eed neural processing. Coinpared with aiialog iieuro chips: digital chips are inferior processing performance, hut superior in operatioiial accuracy and inass productivity.irtheriiiore, it is easy to iiieiiiorizc syiiaplic wcights in digital chips. Recently dig i t a1 ii cur o chips w i 11-1 i nip 1 ciiicii t at i o ii tcch ii o I og X es s~i c h as riiiil ti 'ocessor architecture 111 1 or [he reduction scheme of the nunibeir of calculation 1211 3. 1 tve been developed, aiid higher performance have been achieved. However, those :uro chips are very expeiisive because large size of Ineinory for syiiaptic wei.ghts id several chips are needed to classify large categories. Optimum network size and m e paraiiieters have to be deteriniiied by trial and error in order to obtain better cognition accuracy with less ineinory size. Additionally, those conventional iieiiro lips are 1101 suitable for pattcrii recognition with a large nuiiibcr of categories. Big iLleS of iinpleineiitatioii of iieuro chip ;UC how to dekrininc an approprialc size ol 7803-3550-3/96$5.00C3 1996 559

show abstract

Section: Introductionmentioning

confidence: 99%

“…Thus we have proposed an original proliferating iieuroii inodel [4]. a iiiulti NN inodel [SI and original three new schemes : "architecture lor proliferating neurons".…”

Section: Introductionmentioning

confidence: 99%

A digital neuro chip with adaptive segmentation quantizer neuron architecture (ASQA)

Fukuda¹,

Nakahira²,

Sakiyama³

et al.

Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

A new scheme which incrementally generates neural networks for distorted handprinted Kanji pattern recognition

Kimura

1994

Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)

View full text Add to dashboard Cite

We present a recognition system that incrementally generates neural networks to solve the problem of error caused by sample distribution overlap among categories. The first stage neural network performs the easiest task which is to separate mostly non-overlapping distributions, and leaves the difficult tasks such as separating overlapped distributions to the neural network(s) generated in the following stage(s). The new system improves its performance by assigning tasks to neural networks according to the degree of task difficulty and forms a specialized neural network. The new system achieves higher performance for the recognition of distorted Kanji patterns than the traditional neural networks which consist of only one neural network. The ability of the system to eliminate overlapped distributions is confirmed by analyzing the output distribution of the hidden units.

show abstract

Structured neural networks for multi-font Chinese character recognition using a newly developed digital neural network chip with adaptive segmentation of quantizer neuron architecture (ASQA)

Kondo

Imagawa²,

Maruno³

Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop

View full text Add to dashboard Cite

Adaptive segmentation of quantizer neuron architecture (ASQA)

Cited by 4 publications

References 1 publication

A digital neuro chip with adaptive segmentation quantizer neuron architecture (ASQA)

A digital neuro chip with adaptive segmentation quantizer neuron architecture (ASQA)

A new scheme which incrementally generates neural networks for distorted handprinted Kanji pattern recognition

Structured neural networks for multi-font Chinese character recognition using a newly developed digital neural network chip with adaptive segmentation of quantizer neuron architecture (ASQA)

Contact Info

Product

Resources

About