Neural network signal processor

• US 5,003,490 A
• Filed: 10/07/1988
• Issued: 03/26/1991
• Est. Priority Date: 10/07/1988
• Status: Expired due to Term

• Current Assignee: Hughes Electronics Corporation (Rtx Corporation)
• Original Assignee: Hughes Aircraft Company (Rtx Corporation)
• Inventors: Castelaz, Patrick F., Mills, Dwight E.
• Primary Examiner(s): TARCZA, THOMAS H
• Application Number:
  US07/255,090
• Time in Patent Office: 900 Days
• Field of Search: 364/513, 382/14, 382/15
• US Class Current: 706/22
• CPC Class Codes: G06F 18/24317 Piecewise classification, i.e. whereby each classification requires several discriminant rules
• CPC Class Codes: G06N 3/065 Analogue means

Abstract

A neural network signal processor (NSP) (20) that can accept, as input, unprocessed signals (32), such as those directly from a sensor. Consecutive portions of the input waveform are directed simultaneously to input processing units, or "neurons" (22). Each portion of the input waveform (32) advances through the input neurons (22) until each neuron receives the entire waveform (32). During a training procedure, the NSP 20 receives a training waveform (30) and connective weights, or "synapses" (28) between the neurons are adjusted until a desired output is produced. The NSP (20) is trained to produce a single response while each portion of the input waveform is received by the input neurons (22). Once trained, when an unknown waveform (32) is received by the NSP (20), it will respond with the desired output when the unknown waveform (32) contains some form of the training waveform (30).

Claims

1. In a neural network having a plurality of neurons adapted to receive signals and adapted to present an output, a plurality of connective synapses providing a weighted coupling between said neurons, said neural network being capable of adapting itself to produce a predetermined output in response to an input by changing the value of said weights, the improvement comprising:

a plurality of input neurons adapted to receive external input signals;

means for directing selected, consecutive portions of said input signal directly into said input neurons;

means for advancing said input signal so that the entire input signal from beginning to end is directed to each of said input neurons; and

means for changing said weights to produce said predetermined output during a training procedure each time a portion of a training input is directed to said input neurons, whereby after a plurality of said training procedures, said neural network will respond with said predetermined output to an input signal that is similar to said training input.

2. The neural network of claim 1 wherein a plurality of said input neurons receive different portions of said input signal simultaneously.

3. The neural network of claim 1 wherein said means for directing further comprises a plurality of sampling circuits, each connected to one input neuron for directing a portion of said input signal into said input neuron.

4. The neural network of claim 1 wherein said means for advancing said input signal further comprises:

means for transferring the output signal of each sampling circuit to the input of the next successive sampling circuit; and

timing means for synchronizing the transferring of the output signal from each sampling circuit.

5. The neural network of claim 1 wherein said means for changing said weights further comprises:

means for computing the difference between said desired output and the actual output during training; and

means for minimizing the difference between said desired output and the actual output.

6. The neural network of claim 1 wherein said input signals comprise analog waveforms originating from a sensor.

7. The neural network of claim 1 wherein said desired output is a binary signal produced by a plurality of said neurons.

8. The neural network of claim 1 wherein said neurons further comprise:

a layer of input neurons;

at least one layer of inner neurons; and

a layer of output neurons, wherein said synapses provide a weighted coupling between each neuron and each neuron in each adjacent layer.

9. The neural network of claim 1 wherein said neurons produce an output that depends upon the activation function which takes the form ##EQU4## where y.sub.(ij) is the output of each neuron in the previous layer, w.sub.(ji) is the weight associated with each synapse connecting the neurons in the previous layer to neuron j, and θ

j is a fixed bias.

10. The neural network of claim 5 wherein said means for computing the difference between said desired output and the actual output generates an error signal which is propagated to each neuron, said error signal taking the form

11. A neural network for producing a desired output in response to a particular input signal comprising:

a plurality of neurons adapted to receive signals and adapted to produce an output;

a plurality of connective synapses providing a weighted coupling between said neurons;

said neural network being capable of adapting itself during a training procedure to produce a predetermined output in response to a training input by changing the strength of said weighted connections;

selected ones of said neurons, designated input neurons, adapted to receive external input signals;

means for directing selected consecutive portions of said input signal directly into said input neurons;

means for advancing said input signal so that the entire input signal from beginning to end is directed to each of said input neurons; and

means for changing said weights to produce said predetermined output during a training procedure while a training input advances through said input neurons, whereby after said training procedure said neural network will respond with said predetermined response to an input signal that is similar to said training input.

12. The neural network of claim 11 wherein a plurality of said input neurons receive different portions of said input signal simultaneously.

13. The neural network of claim 11 wherein said means for directing further comprises a plurality sampling circuits each connected to one input neuron for directing a portion of said input signal into said input neuron.

14. The neural network of claim 11 wherein said means for advancing said input signal further comprises:

means for transferring the output signal of each sampling circuit to the input of the next successive sampling circuit; and

timing means for synchronizing the transferring of the output signal from each sampling circuit.

15. The neural network of claim 11 wherein said means for changing said weights further comprises:

means for computing the difference between said desired output and the actual output during training; and

means for minimizing the difference between said desired output and the actual output.

16. The neural network of claim 11 wherein said input signals comprise analog waveforms originating from a sensor.

17. The neural network of claim 11 wherein said desired output is a binary signal produced by a plurality of said neurons.

18. The neural network of claim 11 wherein said neurons further comprise:

a layer of input neurons;

at least one layer of inner neurons; and

a layer of output neurons, wherein said synapses provide a weighted coupling between each neuron and each neuron in each adjacent layer.

19. The neural network of claim 11 wherein said neurons produce an output that depends upon the activation function which takes the form ##EQU5## where y.sub.(ij) is the output of each neuron in the previous layer, w.sub.(ji) is the weight associated with each synapse connecting the neurons in the previous layer to neuron j, and θ

j is a fixed bias.

20. The neural network of claim 15 wherein said means for computing the difference between said desired output and the actual output generates an error signal which is propagated to each neuron, said error signal taking the form

21. A multilayer perceptron for classifying an input waveform comprising:

a plurality of input neurons adapted to receive said input waveform and to produce an output that is a sigmoid function of said input waveform;

a plurality of inner neurons adapted to receive said output signals from said input neurons and adapted to produce an output signal that is a sigmoid function of said received signal;

a plurality for output neurons adapted to receive said output signal from said inner neurons that is a sigmoid function of said received signal;

a plurality of sampling circuits each connected to one input neuron for directing selected, consecutive portions of said input waveform into said input neurons;

means for transferring the output of each sampling circuit to the input of the next successive sampling circuit so that entire input waveform from beginning to end is directed to each of said input neurons in discrete steps;

timing means for synchronizing the transferring of the output signal from each sampling circuit;

means for training said perceptron to produce a predetermined output each time a portion of a training input is directed to said input neurons, including a means for computing the difference between said desired output and the actual output during retaining and means for minimizing the difference between said desired output and the actual output, whereby after a plurality of said training procedures, said perceptron will respond with said predetermined output to an input waveform that is similar to said training input.

25. The method of claim 21 wherein said step of modifying said weighting function comprises changing the weighting functions by an amount

22. A method for classifying an input signal having a characteristic waveform, said method comprising the steps of:

receiving said input signal by a network of processing units;

sampling simultaneously a plurality of consecutive portions of said input signal;

directing said sampled portions of said input signal to a plurality of said processing units;

advancing the sampled portions of the input signal through consecutive ones of said processing units until the entire input signal is sampled;

producing a plurality of intermediate signals by said processing units each of which is a function of said sampled portions of the input signal and an associated weighing function;

producing an output response that is dependent upon at least one of said intermediate signals;

training said network by comparing said output produced in response to a known input signal to a predetermined output, and modifying said weighing function to reduce the difference between the output produced and said desired output; and

comparing the output produced in response to an unknown input widths aid predetermined output, wherein said unknown signal can be classified when said output produced matches said predetermined output.

23. The method of claim 22 wherein said step of advancing said input is accomplished in discrete steps and said weighting function is modified after each discrete step during the training step.

24. The method of claim 22 wherein the step of producing a plurality of intermediate signals and the step of producing an output response both further comprise the step of producing signals in accordance with the activation function ##EQU6##

26. An information processor for classifying an input signal made in accordance with the method comprising:

receiving said input signal by a network of processing units;

sampling simultaneously a plurality of consecutive portions of said input signal;

directing said sampled portions of said input signal to a plurality of said processing units;

advancing the sampled portions of the input signal through consecutive ones of said processing units until the entire input signal is sampled;

producing a plurality of intermediate signals by said processing units each of which is a function of said sampled portions of the input signal and an associated weighing function;

producing an output response that is dependent upon at least one of said intermediate signals;

training said network by comparing said output produced in response to a known input signal to a predetermined output and modifying said weighing function to reduce the difference between the output produced and said predetermined output; and

comparing the output produced in response to an unknown input with said predetermined output, wherein said unknown signal can be classified when said output produced matches said predetermined output.

27. A method for classifying an input signal said method comprising the steps of:

receiving said input signal by a network of processing units;

sampling simultaneously a plurality of consecutive portions of said input signal;

directing said sampled portions of said input signal to a plurality of said processing units;

advancing the sampled portions of the input signal through consecutive ones of said processing units until the entire input signal is sampled;

producing a plurality of intermediate signals by said processing units each of which is a function of said sampled portions of the input signal and an associated weighing function;

producing an output response that is dependent upon at least one of said intermediate signals;

training said network by comparing said output produced in response to a known input signal to a predetermined output and modifying said weighing function to reduce the difference between the output produced and said predetermined output;

comparing the output produced in response to an unknown input with said predetermined output, wherein said unknown signal can be classified when said output produced matches said desired output; and

setting weights in a second network to be the same as those weights in a trained network, whereby an unlimited number of trained networks may be produced from a single trained network.