US5349646A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Signal processing apparatus having at least one neural network
Assignee: Ricoh Co Ltd
•
Filing: 1993-07-20
•
Granted: 1994-09-20
•
Expires: 2013-07-20
Abstract
Abstract A signal processing apparatus for controlling an object includes an input unit, a neural network, an output unit, a teaching unit, and an error signal generator for generating a teaching signal that makes the neural network learn in real time. An error signal generator generates an error signal from the teaching signal and information contained in the network output signal. The error signal controls the neural network so that the control output signal has correct control information with respect to the output signal from the controlled object.
Inventors
- 👤 Toshiyuki Furuta
- 👤 Takashi Kitaguchi
- 👤 Hirotoshi Eguchi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 17:31
CPC Classifications
G; G05; G05B; G05B13/00; G05B13/02; G05B13/0265; G05B13/027
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
231 words
A signal processing apparatus for controlling a controlled object having an output signal, comprising: converting means for converting said output signal of the controlled object into a network input signal, said network input signal being a pulse density signal having a pulse density defined by a number of first values and second values within a predetermined time, the first values and the second values being arranged at random, and the first and second values respectively corresponding to high and low binary signal levels; a neural network for receiving the network input signal and outputting a network output signal which is also a pulse density signal; output means, coupled to said neural network, for converting said network output signal into a control output signal applied to the controlled object; teaching means, coupled to said neural network, for generating a teaching signal for making the neural network learn in real-time; switching means, coupled to said teaching means, for selectively allowing said teaching means to operate such that the neural network is selectively made to learn; and error signal generating means, coupled to said neural network and said teaching means, for generating an error signal using the teaching signal and information contained in said network output signal, said error signal controlling the neural network so that the control output signal has correct control information with respect to the output signal from the controlled object.
Claim 2
Dependent Claim
231 words
A signal processing apparatus for controlling a controlled object having an output signal, comprising: converting means for converting said output signal of the controlled object into a network input signal, said network input signal being a pulse density signal having a pulse density defined by a number of first values and second values within a predetermined time, the first values and the second values being arranged at random, and the first and second values respectively corresponding to high and low binary signal levels; a neural network for receiving the network input signal and outputting a network output signal which is also a pulse density signal; output means, coupled to said neural network, for converting said network output signal into a control output signal applied to the controlled object; teaching means, coupled to said neural network, for generating a teaching signal for making the neural network learn in real-time; switching means, coupled to said teaching means, for selectively allowing said teaching means to operate such that the neural network is selectively made to learn; and error signal generating means, coupled to said neural network and said teaching means, for generating an error signal using the teaching signal and information contained in said network output signal, said error signal controlling the neural network so that the control output signal has correct control information with respect to the output signal from the controlled object.
Claim 3
Dependent Claim
36 words
The signal processing apparatus as claimed in claim 1, wherein said switching means comprises means for periodically making said teaching means operate at predetermined intervals so that the neural network is periodically selectively made to learn.
Claim 4
Dependent Claim
62 words
The signal processing apparatus as claimed in claim 1, wherein said switching means comprises means for determining if at least one of the input signal and the teaching signal satisfies a predetermined condition, and for making said teaching means operate when the means for determining determines that at least one of the input signal and the teaching signal satisfies the predetermined condition.
Claim 5
Dependent Claim
72 words
A signal processing apparatus according to claim 1, wherein said switching means comprises: means, connected to the neural network and the switching means, for cycling the neural network through a plurality of successive cycles, wherein each of said plurality of successive cycles includes a first period for learning in which said teaching means is made to operate by the switching means, followed by a second period for control by the neural network.
Claim 6
Dependent Claim
206 words
A signal processing apparatus for controlling a controlled object having an output signal, comprising: converting means for converting said output signal of the controlled object into a network input signal, said network input signal being a pulse density signal having a pulse density defined by a number of first values and second values within a predetermined time, the first values and the second values being arranged at random, and the first and second values respectively corresponding to high and low binary signal levels; a neural network receiving the network input signal and outputting a network output signal which is also a pulse density signal; and output means, coupled to said neural network, for converting said network output signal [Into]into a control output signal applied to the controlled object; teaching means, coupled to said neural network, for generating a teaching signal for making the neural network learn in real-time; and error signal generating means, coupled to said neural network and said teaching means, for generating an error signal from a teaching signal and information contained in said network output signal, said error signal controlling the neural network so that the control output signal has correct control information with respect to the output signal from the controlled object.
Claim 7
Dependent Claim
206 words
A signal processing apparatus for controlling a controlled object having an output signal, comprising: converting means for converting said output signal of the controlled object into a network input signal, said network input signal being a pulse density signal having a pulse density defined by a number of first values and second values within a predetermined time, the first values and the second values being arranged at random, and the first and second values respectively corresponding to high and low binary signal levels; a neural network receiving the network input signal and outputting a network output signal which is also a pulse density signal; and output means, coupled to said neural network, for converting said network output signal [Into]into a control output signal applied to the controlled object; teaching means, coupled to said neural network, for generating a teaching signal for making the neural network learn in real-time; and error signal generating means, coupled to said neural network and said teaching means, for generating an error signal from a teaching signal and information contained in said network output signal, said error signal controlling the neural network so that the control output signal has correct control information with respect to the output signal from the controlled object.
Claim 8
Dependent Claim
47 words
The signal processing apparatus as claimed in claim 5, further comprising: means, connected to the neural network and the output means, for counting pulse contained in the network output signal; wherein said output means outputs said control output signal having information indicating a number of pulse counted.
Claim 9
Dependent Claim
65 words
The signal processing apparatus as claimed in claim 5, further comprising: means, connected to the neural network, for counting pulses contained in the network output signal; and means, connected to the means for counting and output means, for comparing a number of pulse counted with a predetermined constant threshold value; wherein said output means outputs said control output signal having information indicating a comparison result.
Claim 10
Dependent Claim
70 words
The signal processing apparatus as claimed in claim 5, further comprising: means, connected to the neural network, for counting pulse contained in the network output signal; and means, connected to the means for counting and output means, for comparing a number of pulses counted with a predetermined threshold value externally supplied to the output means; wherein said output means outputs said control output signal having information indicating a comparison result.
Claim 11
Dependent Claim
64 words
The signal processing apparatus as claimed in claim 5, further comprising: means, connected to the neural network, for counting pulse contained in the network output signal; and means, connected to the means for counting and output means, for comparing a number of pulse counted with a variable threshold value; wherein said output means outputs said control output signal having information indicating a comparison result.
References Cited (Backward Citations)
US5167006A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-09-19 | 1998-03-21 | 1998-09-20 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-09-19 | 2002-03-21 | 2002-09-20 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-09-19 | 2006-03-21 | 2006-09-20 | $7700.00 | Window Closed / Lapsed |