Title:
光学的にアドレスされたニューラルネットワーク
Document Type and Number:
Japanese Patent JP3583535
Kind Code:
B2
Abstract:
A compact neural network architecture (10) is trainable to sense and classify an optical image (Figs 3, 6) directly projected onto it. The system is based upon the combination of a two-dimensional array (12) of amorphous silicon photoconductors (18) and a liquid-crystal spatial light modulator (20; Fig. 2). Appropriate filtering of the incident optical image upon capture is incorporated into the network training rules, through a modification of the standard backpropagation training algorithm. Training of the network (10) on two image classification problems is described: the recognition of handprinted digits (Fig. 3), and facial recognition (Fig. 6). The network (10), once trained is capable of standalone operation, sensing an incident image and outputting a final classification signal in real time.
Inventors:
Richard G. Stearns
Application Number:
JP34563795A
Publication Date:
November 04, 2004
Filing Date:
December 08, 1995
Export Citation:
Assignee:
XEROX CORPORATION
International Classes:
G06E3/00; G06F15/18; G06N3/00; G06G7/60; G06N3/067; G06T1/40; G06V10/20; (IPC1-7): G06E3/00; G06G7/60; G06N3/067
Domestic Patent References:
| JP5011303A | ||||
| JP3188554A |
Other References:
有馬裕、田中健一、太田淳、森伯郎、久間和生,最近の信号処理 ニューロチップの最近の話題,システム/制御/情報,日本,システム制御情報学会,1994年 8月15日,第38巻第8号,p.13-19
Attorney, Agent or Firm:
Atsushi Nakajima
Kato Kazunori
Kato Kazunori