Sensor for use in a neural network

• US 5,675,713 A
• Filed: 06/07/1995
• Issued: 10/07/1997
• Est. Priority Date: 12/22/1993
• Status: Expired due to Fees

• Current Assignee: George W. Batten Jr
• Original Assignee: George W. Batten Jr
• Inventors: Batten, George W. Jr.
• Primary Examiner(s): Davis, George B.
• Application Number:
  US08/480,122
• Time in Patent Office: 853 Days
• Field of Search: 395/22, 395/24
• US Class Current: 706/26
• CPC Class Codes: G06N 3/063 using electronic means

Abstract

An artificial neuron for use in a neural processing network comprises a plurality of input signal lines, an arrangement for computing a nonlinear function of the sum of the inputs multiplied by associated weights, and a saturating delta-sigma modulator which oversamples the computed value and produces an encoded neuron output signal. Conversion of signals for use by these neurons preferably is performed by delta-sigma modulators at the inputs to the neurons, which may be incorporated directly into sensors. Processing of the output signals from the neuron includes low-pass filtering and decimation. The present invention may be used in many diverse areas. For example, arrays of sensors with delta signal modulators may be coupled with a network of the neurons to form an intelligent vision system. Linear signal processing, both conventional and adaptive, can be done by a simple neuronal system that operates linearly.

Claims

1. A sensor for use in a neural network, comprising:

a sensor for sensing a parameter and outputting an analog signal;

an integrator coupled to said sensor, said integrator receiving the analog signal and outputting an integrated signal;

a comparator receiving said integrated signal and comparing said integrated signal with a reference value, and producing a two-state signal in response;

a latch receiving said two-state signal, and providing an output signal to said neural network.

2. A sensor as in claim 1, wherein the output signal of said latch is provided as an input signal to a controlled source, said controlled source producing a feedback signal that is applied as an input to said integrator.

3. A sensor as in claim 1, wherein said neural network comprises a network of delta sigma neurons, each of which comprises a neuron input unit and a delta sigma modulator.

4. A sensor as in claim 1, wherein said sensor comprises a photosensor.

5. A sensor as in claim 4, wherein said neural network comprises an intelligent vision system.