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 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.
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 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 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:
There is provided a head driving device for causing a head to discharge droplets. The device includes a drive circuit, a first drive waveform generation circuit, a second drive waveform generation circuit, and a correction circuit. The drive circuit is configured to drive the head based on a plurality of drive waveforms to discharge the droplets. The first drive waveform generation circuit configured to generate a first drive waveform of the plurality of drive waveforms. The second drive waveform generation circuit is configured to generate a second drive waveform of the plurality of drive waveforms. The correction circuit is configured to correct the first drive waveform and the second drive waveform with reference to an intermediate potential.
摘要:
An information processor that is connected to at least one other information processor via a network, includes a detecting unit that detects an optional device to be used for information processing, as a target optional device, installed on the other information processor, an issuing unit that issues an access request to use the target optional device to the other information processor, a receiving unit that receives an access permission for access to the target optional device from the other information processor, and a processing unit that performs the information processing with the target optional device.
摘要:
A high-speed serial switch fabric is configured to perform a mapping of a traffic class that is capable of differentiating traffics onto a virtual channel. The high-speed serial switch fabric connects a plurality of devices. A traffic-class setting unit sets, when a conflict occurs between devices connected to the high-speed serial switch fabric, the traffic class for each of traffics in the devices having the conflict. A channel setting unit assigns each of set traffic classes to different virtual channels, and gives a priority of data communication to each of the set traffic classes.