摘要:
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.
摘要:
A neuron unit processes a plurality of input signals and for outputs an output signal which is indicative of a result of the processing, and includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a function generating part for generating new weight functions based on errors between the output signal of the forward process part and teaching signals and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part. The supplying part includes a memory for storing each weight function in the form of a binary value, and a generating circuit for generating a random pulse train based on each binary value stored in the memory. The random pulse train describes each weight function in the form of a pulse signal having a pulse density.
摘要:
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.
摘要:
A neuron unit processes a plurality of input signals and outputs an output signal which is indicative of a result of the processing. The neuron unit includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a generating part for generating new weight functions based on errors between the output signal of the forward process part and teaching signals and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part.
摘要:
A hierarchical signal processing apparatus includes aggregates having logic operation portions. The apparatus compares a final output signal from a logic operation portion in a final aggregate with a teaching signal, and generates an error signal by taking a signal which exists only in the teaching signal as a positive error signal, and taking a signal which exists only in said final output signal as a negative error signal. An error signal generating portion in the apparatus generates a positive error signal of a logic operating portion within a certain aggregate which supplies one or more output signals thereof to said logic operation means of another aggregate based on one or more logic operations on the excitatory weight function signal of said weight function signal, the positive error signal, the inhibitory weight function signal of said weight function signal and the negative error signal, and also generates a negative error signal of said logic operation means within said certain aggregate which supplies one or more output signals thereof to said logic operation means of said other aggregate based on one or more logic operations on the inhibitory weight function signal of said weight function signal, the positive error signal of said other aggregate, the excitatory weight function signal of said weight function signal and the negative error signal.
摘要:
A neuron unit processes a plurality of input signals and outputs an output signal which is indicative of a result of the processing. The neuron unit includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a generating part for generating new weight functions based on errors between the output signal of the forward process part and teaching signals and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part.
摘要:
A neuron unit simultaneously processes a plurality of binary input signals. The neuron unit includes input lines for receiving first and second input signals which undergo transitions with time, first and second memories for storing weighting coefficients, a first gate for successively obtaining a logical product of one of the first input signals and a corresponding one of the weighting coefficients read out from the first memory for each of the first input signals, a second gate for successively obtaining a logical product of one of the second input signals and a corresponding one of the weighting coefficients read out from the second memory for each of the second input signals, a third gate for obtaining a logical sum of logical products output from the first gate, a fourth gate for obtaining a logical sum of logical products output from the second gate, and an output part including an inverter for inverting the logical sum output from the fourth gate and a gate for obtaining one of a logical product and a logical sum of the logical sum output from the third gate and an inverted logical sum output from the inverter. This gate outputs an output signal of the neuron unit.
摘要:
A neuron unit processes a plurality of input signals and outputs an output signal which is indicative of a result of the processing. The neuron unit includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a generating part for generating new weight functions based on an error signal representing an error between the output signal of the forward process part and a teaching signal and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part. The error signal includes first and second error signal components representing pulse densities.
摘要:
A neuron unit simultaneously processes a plurality of binary input signals. The neuron unit includes input lines for receiving first and second input signals which undergo transitions with time, first and second memories for storing weighting coefficients, a first gate for successively obtaining a logical product of one of the first input signals and a corresponding one of the weighting coefficients read out from the first memory for each of the first input signals, a second gate for successively obtaining a logical product of one of the second input signals and a corresponding one of the weighting coefficients read out from the second memory for each of the second input signals, a third gate for obtaining a logical sum of logical products output from the first gate, a fourth gate for obtaining a logical sum of logical products output from the second gate, and an output part including an inverter for inverting the logical sum output from the fourth gate and a gate for obtaining one of a logical product and a logical sum of the logical sum output from the third gate and an inverted logical sum output from the inverter. This gate outputs an output signal of the neuron unit.
摘要:
A neuron unit processes a plurality of binary input signals and outputs a neuron output signal which is indicative of a result of the processing. The neuron unit is provided with a plurality of first gates respectively for carrying out a logical operation on a binary input signal and a weighting coefficient, a second gate for carrying out a logical operation on an excitatory output signal of each of the first gates, a third gate for carrying out a logic operation on an inhibitory output signal of each of the first gates, a fourth gate for synthesizing output signals of the second and third gates and outputting the neuron output signal, and a generating circuit for generating the weighting coefficients which are supplied to each of the first gates. The generating circuit for generating one weighting coefficient includes a random number generator for generating random numbers, and a comparator for comparing each random number r with a predetermined value q and for outputting a pulse signal having first and second values depending on whether each random number r is such that r.ltoreq.q or r>q, and each weighting coefficient is described by a pulse density.