JPH05108594A - Signal processor - Google Patents

Abstract

PURPOSE:To improve the versatility of neuron and to make the device easy to be used by realizing digital configuration so as to secure operations and to facilitate turning to a hardware. CONSTITUTION:Memories 26a, 26b are provided to hold the pair of two coupling coefficients showing excited coupling and suppressed coupling in respect to plural input signals 25, versatility is realized so as not to limit the coupling between neurons into the excited coupling or the suppressed coupling, ANDing means 27a, 27b AND the input signals 25 and the respective coupling coefficients, afterwards, the calculated results of these ANDing means 27a, 27b are ORed by first ORing means 28a, 28b with the same pair and therefore, both couplins are properly grouped into the excited coupling group and the suppressed coupling group so as not to be realized at the same time. Afterwards, a prescribed operation processing is executed concerning the ANDed and ORed results by groups.

Description

Detailed Description of the Invention

[0001]

INDUSTRIAL APPLICABILITY The present invention is applicable to control of various movements such as image and voice recognition, position control of robots, temperature control of air conditioners, orbit control of rockets, etc. The present invention relates to a signal processing device such as a neural computer.

[0002]

2. Description of the Related Art The function of a nerve cell (neuron), which is a basic unit of information processing of a living body, is mimicked, and further, this "nerve cell mimicking element" (nerve cell unit) is connected to a network to process information in parallel. The aim is a so-called neural network. Although it is easy to perform character recognition, associative memory, motion control, etc. in a living body, there are many things that conventional Neumann computers cannot easily achieve. There have been many attempts to solve these problems by imitating a neural system of a living body, in particular, a function peculiar to the living body, that is, parallel processing, self-learning, etc. by a neural network.

First, a conventional neural network model will be described. FIG. 21 is a diagram showing a certain nerve cell unit A, and FIG. 22 is a network thereof. A ₁ , A ₂ , and A ₃ each represent a nerve cell unit. One neuronal cell unit is coupled to a number of other neuronal cell units and processes the signals received from them to produce an output. In the case of FIG. 22, the network is hierarchical, and the nerve cell unit A ₂ receives a signal from the nerve cell unit A _{1 in the} previous layer (left side) and the nerve cell unit A in the next layer (right side). Output to ₃ .

A more detailed description will be given. First, in the nerve cell unit A of FIG. 21, the degree of coupling between another nerve cell unit and its own unit is called a coupling coefficient, and the coupling coefficient of the i-th nerve cell unit and the j-th nerve cell unit The coupling coefficient is generally represented by T _ij . For the coupling, excitatory coupling in which the larger the signal from the other unit (the unit that sends a signal to the own unit) is, the larger the own unit output is, and the larger the signal from the other unit is, the own unit output Is an inhibitory bond, where T _ij > 0 represents an excitatory bond, and T _ij <0 represents an inhibitory bond. Now, let's say that our nerve cell unit is the jth unit, and the output of the ith nerve cell unit is y.
_{If it is i} , T _ij y _{i obtained} by multiplying this by the coupling coefficient T _ij becomes the input to the own unit. As described above, since one nerve cell unit is connected to many nerve cell units, ΣT _ij y _{i, which} is the result of adding T _ij y _i for these units, is It becomes an input to the unit. This is called the internal potential and is represented by u _j .

[0005]

[Equation 1]

Next, a threshold value is added to this input (internal potential) to perform non-linear processing, and the result is output from the nerve cell unit. The function used at this time is called a nerve cell response function, and the sigmoid function as shown in equation (2) and FIG. 23 is used as the nonlinear function.

[0007]

[Equation 2]

When such a nerve cell unit is constructed in a network as shown in FIG. 22, each coupling coefficient T
By providing _ij and sequentially calculating equations (1) and (2), parallel processing of information becomes possible and a final output is obtained.

In such a hierarchical neural network, a desired neural network is constructed by performing learning such that the coupling coefficient T _ij is updated so that a desired result is output for a certain input. .. The most widely used such learning method is the error back-propagation method, so-called back-propagation method.

An example of such a network realized by an electric circuit is shown in FIG. This is disclosed in Japanese Patent Laid-Open No. 62-295188, and basically, a plurality of amplifiers 1 having an S-shaped transfer function, and the output of each amplifier 1 is input to the input of the amplifier of another layer. A resistive feedback network 2 is provided which is connected as shown by the dashed line. The input side of each amplifier 1 has a C connected by a grounded capacitor and a grounded resistor.
The R time constant circuits 3 are individually connected. Then, the input current _{I 1, I 2, ~,} I n is supplied to the input of the amplifier 1, the output is obtained from a set of these amplifiers 1 output voltage.

Here, the signal strength of the input and output to the network is represented by a voltage, and the strength of the coupling between the nerve cell units is the resistance 4 (in the resistive feedback network 2) connecting the input / output lines between the cells. Is represented by the resistance value of each of the amplifiers 1, and the nerve cell response function is represented by the transfer function of each amplifier 1. That is, in FIG. 24, the plurality of amplifiers 1 have an inverting output and a non-inverting output, and each input of the amplifiers 1 has a CR time constant circuit 3 as an input current supply means, which is selected in advance. The feedback network 2 connects each output of the amplifier 3 to the input by a resistor 4 (T _ij ) having a value of 1 or a second value selected in advance. Resistor 4 represents the transconductance between the i-th amplifier output and the j-th amplifier input and is chosen to create multiple minima that the network will balance to minimize the energy function with multiple minima. I am trying to In addition, the coupling between nerve cells has excitability and inhibitory property, and is mathematically represented by the sign of the coupling coefficient, but it is difficult to realize the sign with a constant on the circuit. Then, by dividing the output of the amplifier 1 into two and inverting one output, positive and negative 2
It is realized by generating two signals and selecting them appropriately. Further, an amplifier is used as the one corresponding to the sigmoid function shown in FIG.

On the other hand, an example in which a neural network is realized by a digital circuit will be described with reference to FIGS. FIG. 25 shows a circuit configuration of a single nerve cell, in which each synapse circuit 6 is connected to a cell body circuit 8 via a dendrite circuit 7. FIG. 26 shows an example of the configuration of the synapse circuit 6 in which the input pulse f is multiplied by a factor a through the coefficient circuit 9.
A rate multiplier 10 to which a value obtained by multiplying (a multiplication factor of 1 or 2 by the feedback signal) is input is provided, and the rate multiplier 10 is connected to a synapse weight register 11 that stores a weighting value w. . Further, FIG. 27 shows a configuration example of the cell body circuit 8, and the control circuit 1
2, an up / down counter 13, a rate multiplier 14 and a gate 15 are sequentially connected, and an up / down memory 16 is further provided.

[0013] In this, the input and output of the nerve cell unit is represented by a pulse train, and the pulse density represents the amount of signal.
The coupling coefficient is represented by a binary number and stored in the memory 16. By inputting the input signal into the clock of the rate multiplier 14 and inputting the coupling coefficient into the rate value,
The pulse density of the input signal is reduced according to the rate value. This is the T _{ij of the} backpropagation model equation.
It corresponds to the part of y _i . Next, the Σ portion of ΣT _ij y _i is realized by the OR circuit shown by the dendrite circuit 7. Since the coupling has excitatory and inhibitory properties, it is divided into groups in advance and OR is taken for each group. An output is obtained by inputting these two outputs to the up side and down side of the counter 13 and counting. This output is 2
Since it is a decimal number, the rate multiplier 14 is used again to convert it into a pulse density. A neural network can be realized by making this unit a network.

[0014]

However, the former analog circuit system has the following problems. The signal strength is represented by an analog value such as electric potential or current,
When the internal calculation is also performed in an analog manner, its value changes due to temperature characteristics, drift immediately after power-on, and the like. Since it is a network, a large number of elements are required, but it is difficult to make the respective characteristics uniform. When the accuracy or stability of one element becomes a problem, it may cause a new problem when it is used as a network, and the behavior when viewed in the whole network cannot be predicted. Since the coupling coefficient T _ij is fixed and the value learned in advance by another method such as simulation is used, self-learning cannot be performed.

Also, in the latter case of the network configuration of digital circuits, the up / down counter 1 is actually used.
3. Use of the rate multiplier 14 results in a very complicated and large-scale circuit.

As described above, according to the prior art, the analog circuit system is not reliable in operation, and the learning method by numerical calculation is complicated in calculation. The circuit configuration is large and complicated.

In order to solve such a drawback, a simple signal processing method or device which performs a calculation inside the network by a digital circuit configuration which ensures reliable operation and facilitates hardware implementation is disclosed in Japanese Patent Application No. 4124848
And Japanese Patent Application No. 3-29342. Further, it has been proposed to increase the flexibility of neurons by simultaneously having two coupling coefficients, excitatory and inhibitory, with respect to the coupling between one neuron and another neuron. No more appropriate arithmetic processing is mentioned.

[0018]

According to a first aspect of the present invention, a memory that holds two sets of coupling coefficients of excitatory coupling and inhibitory coupling for a plurality of input signals, and the input signal. The logical product calculating means for calculating a logical product with each of the coupling coefficients, the first logical calculating means for performing a logical operation on the same result by the logical product calculating means, and the first logical calculating means An OR operation means for dividing an operation result into an excitatory connection group and an inhibitory connection group and performing an OR operation in each group, and a logical operation of the operation results of these OR operation means, and outputting an output signal. A signal processing means having a second calculating means for obtaining is provided, and in the invention according to claim 2, the signal processing means has a coupling coefficient varying means for varying each coupling coefficient stored in the memory. Contract In the invention of claim 3, and connecting a plurality of signal processing means net.

[0019]

[Function] Since the coupling includes excitatory coupling and inhibitory coupling, flexibility is provided by having a pair of coupling coefficients of excitatory coupling and inhibitory coupling for each input signal. Appropriate for the excitatory coupling group and the inhibitory coupling group so that the logical product processing result of each coupling coefficient and the input signal is processed by the first logical operation means and the result does not have both couplings at the same time. Then, the logical OR operation and the predetermined operation processing of the operation result are performed for each group, so that an appropriate output signal can be obtained with a simple digital circuit configuration only by the logical processing. At this time, by varying each coupling coefficient stored in the memory by the coupling coefficient varying means, a self-learning function can be provided, and flexibility and capability can be improved. By connecting the signal processing means having such a function like a net, a highly flexible neural network system can be constructed.

[0020]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described with reference to FIGS. First, a nerve cell unit (neuron element) and a neural network using a digital logic circuit having a self-learning function will be described.

First, the neurons and neural networks of this embodiment are digitalized and implemented as hardware, but the basic idea is to input / output signals, intermediate signals,
The coupling coefficient, the teacher signal, etc. are all represented by a binary pulse train of "0" and "1". The amount of signal inside the network is represented by the pulse density (the number of "1" s within a certain fixed time). The calculation in the nerve cell unit is represented by a logical operation between pulse trains. The pulse train of the coupling coefficient is placed in the memory. Learning is realized by rewriting this pulse train. For learning, the error is calculated based on the given teacher signal pulse train, and the coupling coefficient pulse train is changed based on the error. At this time, the calculation of the error and the change of the coupling coefficient are all performed by the logical operation of the pulse train of "0" and "1". It was done like this.

The idea will be described below. First,
Regarding signal processing by a digital logic circuit, signal processing in the forward process will be described. FIG. 2 shows a portion corresponding to one nerve cell unit (nerve cell mimicking element) 20, and the neural network as a whole is of a hierarchical type as shown in FIG. Input and output are all
The one that is binarized into “1” and “0” and synchronized is used. The value (intensity) of the input signal y _i is represented by a pulse density, and is represented by the number of states of “1” within a certain time as in the pulse train shown in FIG. 4, for example. That is, the example of FIG.
4/6, and the signal "1" is 4 in 6 sync pulses.
There are two "0" s. At this time, it is desirable that the arrangement of "1" and "0" is random.

On the other hand, the coupling coefficient T _ij indicating the degree of coupling between the nerve cell units 20 is also expressed by pulse density,
The pulse train of "0" and "1" is prepared in advance in the memory. The example of FIG. 5 is an expression representing “101010” = 3/6. Also in this case, it is desirable that the arrangement of "1" and "0" is random.

Then, this coupling coefficient pulse train is sequentially read from the memory in response to the synchronous clock, and as shown in FIG. 2, each AND gate 21 ANDs with the input signal pulse train (y _i ∩ T _ij ). This is used as an input to the nerve cell j. In the case of the above example, the input signal is “10
When input as "1101", a pulse train is called from the memory in synchronism with this, and "101000" as shown in FIG. 6 is obtained by sequentially performing AND, which means that the input y _i is the coupling coefficient T _ij. It is shown that the pulse density becomes 2/6 by the conversion.

The pulse density of the output of the AND gate 21 is
It is approximately the product of the pulse density of the input signal and the pulse density of the coupling coefficient, and has the same function as the analog coupling coefficient. This is because the longer the signal train is, the more "1"
The more random the arrangement of "0" and "0", the closer to the product of numerical values it has. When the pulse train of the coupling coefficient is shorter than the input pulse train and there is no data to be read, the head of the data may be returned to and the reading may be repeated.

Since one nerve cell unit 20 has multiple inputs, there are also many "ANDs of the input signal and the coupling coefficient" described above, and then the OR circuit 22 takes the logical sum of these. Since the inputs are synchronized, for example, the first data is "101000" and the second data is "01000".
In the case of “0”, the OR of both is “111000”. If multiple inputs (m pieces) are calculated at the same time and they are output, it becomes as shown in FIG. 7, for example. This is the sum calculation and non-linear function (sigmoid function) in analog calculation.
It corresponds to the part of.

When the pulse density is low, the pulse density of its OR is approximately equal to the sum of the pulse densities. As the pulse density increases, the OR circuit 22
Since the output of is gradually saturated, it does not match the sum of pulse densities, and nonlinearity appears. In the case of OR, the pulse density does not become larger than 1 and does not become smaller than 0, and is a monotonically increasing function, which is approximately equivalent to the sigmoid function.

By the way, although the coupling has excitability and inhibitory property, the pulse density cannot express the negative. Therefore, in this embodiment, first, in the coupling between the neurons, the excitatory coupling coefficient and the inhibitory coupling coefficient are combined. Have both at the same time.
That is, it is assumed that a combination of a positive coupling coefficient T _{ij (+)} and a negative coupling coefficient T _{ij (−)} exists for one coupling at the same time.
Then, the input signal and the respective coupling coefficients T _{ij (+)} and T _{ij (-)}
The AND output result of and is compared between the groups, and the output from each group is divided into an excitatory coupling group and an inhibitory coupling group. Specifically, when the output from the excitatory coupling side is "1" and the output from the inhibitory coupling side is "0", the output to the excitatory coupling group is "1" and the output to the inhibitory coupling group is "0". ". On the contrary, when the output from the excitatory coupling side is “0” and the output from the inhibitory coupling side is “1”, the output to the excitatory coupling group is “0” and the output to the inhibitory coupling group is “1”. ". In other cases, the outputs to both groups of excitatory and inhibitory connections are set to "0". That is, even if both the excitatory coupling side and the inhibitory coupling side become “1”, they are offset in grouping, and the degree of adverse effect is reduced.

After grouping in this way, an OR operation is performed within each group, and a predetermined logical operation process is performed on the OR operation result to determine the output signal of the neuron. For example, "1" is output only when the OR result of the excitatory coupling group is "1" and the OR result of the inhibitory coupling group is "0", and "0" is output otherwise.

When expressed by a logical expression, it is expressed by the following expressions (3) to (5).

[0031]

[Equation 3]

The network of nerve cell units 20 is
Hierarchical type similar to backpropagation (ie, Figure 3)
And If the entire network is synchronized, each layer can be calculated by the functions described above.

Next, the signal calculation processing in learning (back propagation) will be described. Basically, the error signal may be obtained by the following a or b, and then the value of the coupling coefficient may be changed by the method of c.

First, the error signal in the final layer will be described as a. In the final layer, the error signal in each nerve cell unit is calculated by the output signal and the teacher signal. Here, a desired output with respect to the input at that time is given by a pulse train as a teacher signal. Generally, if the error is expressed by a numerical value, it can take both positive and negative values, but since it cannot be expressed simultaneously by the pulse density, an error signal can be obtained by using two kinds of signals, one representing a + component and the other representing a − component. Express. That is,
The error signal of the jth nerve cell unit is shown in FIG. In other words, the + component of the error signal is the portion (1, 0) or (0,
Among 1), the pulse existing on the teacher signal side, on the other hand, the-component is the pulse existing on the output side as well. In other words,
Error signal + pulse is added to the output pulse, and error signal −
Removing the pulse will result in a teacher pulse. That is, when these positive and negative error signals δ _{j (+)} and δ _{j (-)} are expressed by logical expressions, the expressions (6) and (7) are obtained. The coupling coefficient is changed based on such an error signal pulse as described later.

[0035]

[Equation 4]

Next, a method of obtaining an error signal in the intermediate layer as b will be described. First, the above-mentioned error signal is back-propagated to change not only the coupling coefficient between the final layer and the layer immediately before it, but also the coupling coefficient of the layer before that. Therefore, it is necessary to calculate the error signal in each nerve cell unit in the middle layer. Signals are propagated from a neuron unit with an intermediate layer to each neuron unit in the next layer, which is exactly the reverse of the procedure of collecting error signals in each neuron unit in the next layer. And use it as its own error signal. This can be performed in the same manner as the above-described arithmetic expressions (3) to (5) and the cases shown in FIGS. 4 to 8 in the nerve cell unit. However, the difference from the above-mentioned processing in the nerve cell unit is that y is one signal, while δ has two signals as a signal showing positive and negative, and both signals are considered. It is necessary. Therefore, it is necessary to divide into two cases depending on whether the coupling coefficient T is positive or negative.

First, the case of excitatory coupling will be described. In this case, for a nerve cell unit having an intermediate layer, the error signal + at the jth nerve cell unit of the layer immediately before (the last layer in FIG. 3), the nerve cell unit and self (intermediate layer in FIG. 3) For each nerve cell unit, an AND (δ _{j (+)} ∩ T _ij ) of the coupling coefficient with a certain nerve cell unit) is obtained, and the OR between them is taken {∪ (δ _{j (+)} ∩ T _ij )}. This is defined as the error signal + of its own nerve cell unit. That is, it becomes as shown in FIG.

Similarly, the error signal of the nerve cell unit of the previous layer is ANDed with the coupling coefficient, and the difference between them is ORed to obtain the error signal of its own nerve cell unit. .. That is, it becomes as shown in FIG.

Next, the case of inhibitory binding will be described. In this case, the AND of the error signal in the nerve cell unit of the layer one layer ahead and the coupling coefficient of the nerve cell unit and the self is taken, and further the OR between them is taken. This is defined as the error signal + of its own nerve cell unit. That is, it becomes as shown in FIG.

Further, by ANDing the preceding error signal + and the coupling coefficient and further ORing them, the error signal − of its own nerve cell unit is similarly obtained. That is, it becomes as shown in FIG.

Further, the error signal + of the excitatory connection and the error signal + of the inhibitory connection of this nerve cell unit are ORed, and this is taken as the error signal δ _{i (+)} of this unit. Similarly, the error signal of the excitatory coupling and the error signal of the inhibitory coupling are ORed, and this is calculated as the error signal δ of this unit.
_{i (-)}

The above is summarized as shown in equation (8).

[0043]

[Equation 5]

Further, a function corresponding to the learning rate (learning constant) may be provided. When the rate is 1 or less in the numerical calculation, the learning ability is further enhanced. This can be realized by thinning out the pulse train in the pulse train calculation. In the present embodiment, a counter-like idea is adopted and the one shown in FIGS. 14 and 15 is adopted. For example, at the learning rate η = 0.5, every other pulse train of the original signal is thinned out, but even if the pulses of the original signal are not evenly spaced, it is possible to thin out the original pulse train. In FIGS. 14 and 15, when η = 0.5, every other pulse is thinned out, when η = 0.33, every two pulses are left, and when η = 0.67, two pulses are left. Indicates that every other thinning is performed once.

Thus, the learning rate function is provided by thinning out the error signal. Such thinning out of the error signal can be easily realized by logically operating the output of a counter commercially available or using a flip-flop. In particular, when a counter is used, the value of the learning constant η can be set arbitrarily and easily, so that the characteristics of the network can be controlled.

Further, as c, a method of changing each coupling coefficient by such an error signal will be described. The output y _i from the immediately preceding neuron unit and the error signal δ _{j (+)} or δ _{j (} -of the own neuron unit corresponding to the line to which the coupling coefficient to be changed belongs (see FIG. 3) ₎ And (δ _j ∩ y _i ) (see FIGS. 16 and 17).
The two signals thus obtained are respectively expressed by ΔT _{ij (+)} ,
Let ΔT _{ij (-)} .

Then, based on this ΔT _ij , a new T
_ij is obtained. Since this T _ij is an absolute value component, it is classified depending on whether the original T _ij is excitatory or inhibitory. In the case of excitability, the component of ΔT _{ij (+)} is increased with respect to the original T _ij , and ΔT
Reduce the components of _{ij (-)} . That is, it becomes as shown in FIG. On the contrary, in the case of the suppressive property, the component of ΔT _{ij (+)} is reduced and the component of ΔT _{ij (−)} is increased with respect to the original T _ij . That is, FIG.
It becomes as shown in 9.

The above can be summarized as in equation (9).

[0049]

[Equation 6]

The network is calculated based on the above learning rule.

Next, an actual circuit configuration based on the above algorithm will be described. 1 and 20 show examples of the circuit configuration, the configuration of the entire network is the same as that in FIG. FIG. 1 shows a circuit of a portion corresponding to a line (connection) in FIG. 3, and FIG. 20 shows a circle (each nerve cell unit 2 in FIG. 3).
The circuit of the part corresponding to 0) is shown. A digital neural network capable of self-learning can be realized by forming the circuits having the configurations of FIGS. 1 and 20 into a network as shown in FIG.

First, FIG. 1 will be described. In the figure, 25 is an input signal to the nerve cell unit and corresponds to FIG.
The value of the coupling coefficient as shown in FIG. 5 is individually stored in each set of memories, specifically, in the shift registers 26a and 26b. These shift registers 26a and 26b are
The shift register may have a function similar to that of a normal shift register, and may be, for example, a combination of a RAM and an address controller. Here, one shift register 26a stores the excitatory coupling coefficient, and the other shift register 26b stores the inhibitory coupling coefficient. The contents sequentially read from these shift registers 26a and 26b are input together with the input signal 25 to AND gates 27a and 27b, which serve as a logical product calculating means, and logical products are taken. Such logical product results include those of excitatory type and inhibitory type of coupling, and the AND gates 28a, 2a with one-sided inverters respectively serving as first logical operation means.
8b is processed and grouped into an output 29 to the excitatory coupling group and an output 30 to the inhibitory coupling group. That is, in the AND gate 28a, the output 29 for the excitatory coupling group is obtained by removing the influence of the output of the AND gate 27b on the inhibitory side from the output of the AND gate 27a on the excitatory side.
In the ND gate 28b, the AND gate 2 on the inhibitory side
The output of the AND gate 27a on the excitatory side is removed from the 7b output to obtain the output 30 for the inhibitory coupling group.

Further, as shown in FIG. 20, gate circuits 33a and 33b are provided as OR operation means in a plurality of OR gate configurations for performing respective input processes (corresponding to FIG. 7).
Further, as shown in FIG. 8, the output "1" is output only when the excitatory coupling group shown in FIG. 8 is "1" and the inhibitory coupling group is "0". 0 ”
There is provided a gate circuit 34 as a second logical operation means by an AND gate 34a for outputting and an inverter 34b.

Next, the error signal will be described. Figure 20
Error signals 35 and 36 are input to the circuit shown in FIG. These error signals 35 and 36 are collected by a gate circuit 37 having a plurality of OR gates (processing of equation (8)), and then the processing corresponding to the learning rate (processing of FIGS. 14 and 15) is divided. The error signal 3 received by the circuit 38 for the previous layer
It is output as 9,40. Here, the processing as shown in FIGS. 10 to 13 for calculating the error signal in the intermediate layer is performed by the gate circuit 41 having the AND gate and OR gate configuration shown in FIG. Error signal 42 for output to the neuron unit of the previous layer,
43 is obtained.

Further, in this embodiment, 1 is set for each input 25.
Since the pair of shift registers 26a and 26b is provided, the coupling coefficient is rewritten by the self-learning function for each shift register 26a and 26b. Therefore, as shown in FIG. 1, by using the + and − error signals 39 and 40, AND gates and inverters for performing the processes of FIGS. 10 to 13 and the formula (8) for calculating a new coupling coefficient. , OR gate configuration coupling coefficient variable circuit 45 is provided and connected to the data inlet side of each shift register 26a, 26b. According to this method, the connection of the nerve cell units is not limited to excitatory or inhibitory, so that the network has flexibility and has versatility in actual applications.

It should be noted that the present invention is not limited to the above-described configuration example as long as it has equivalent functions.
Further, some or all of them may be realized by software without configuring all by hardware.

[0057]

Since the present invention is configured as described above, according to the invention described in claim 1, since there are excitatory coupling and inhibitory coupling in the coupling, excitatory coupling is performed for each input signal. By having a pair of coupling coefficients of and inhibitory coupling, the connection between each neuron is not limited to excitatory or inhibitory, so that the network has flexibility and has versatility in actual applications. At this time, the first logical operation means processes the logical product processing result of each coupling coefficient and the input signal to obtain a result in which both couplings are not held at the same time. Properly classify the group into a combined group, and then perform OR operation and predetermined operation processing on the operation result for each group, so that an appropriate output signal can be obtained by a simple digital circuit configuration only by logical operation. According to the invention described in claim 2, since each coupling coefficient stored in the memory can be varied by the coupling coefficient varying means, it becomes possible to provide a self-learning function. According to the invention of claim 3, the signal processing means having such a function is connected like a net to construct a highly flexible neural network system. It will be possible.

[Brief description of drawings]

FIG. 1 is a logic circuit diagram showing a main part of an embodiment of the present invention.

FIG. 2 is a logic circuit diagram for performing basic signal processing.

FIG. 3 is a schematic diagram showing a network configuration example.

FIG. 4 is a timing chart showing an example of logical operation.

FIG. 5 is a timing chart showing an example of logical operation.

FIG. 6 is a timing chart showing an example of logical operation.

FIG. 7 is a timing chart showing an example of logical operation.

FIG. 8 is a timing chart showing an example of logical operation.

FIG. 9 is a timing chart showing an example of logical operation.

FIG. 10 is a timing chart showing an example of logical operation.

FIG. 11 is a timing chart showing an example of logical operation.

FIG. 12 is a timing chart showing an example of logical operation.

FIG. 13 is a timing chart showing an example of logical operation.

FIG. 14 is a timing chart showing an example of logical operation.

FIG. 15 is a timing chart showing an example of logical operation.

FIG. 16 is a timing chart showing an example of logical operation.

FIG. 17 is a timing chart showing an example of logical operation.

FIG. 18 is a timing chart showing an example of logical operation.

FIG. 19 is a timing chart showing an example of logical operation.

FIG. 20 is a logic circuit diagram showing a configuration example of each unit.

FIG. 21 is a conceptual diagram showing one unit configuration showing a conventional example.

FIG. 22 is a conceptual diagram of the neural network configuration.

FIG. 23 is a graph showing a sigmoid function.

FIG. 24 is a circuit diagram showing a specific configuration of one unit.

FIG. 25 is a block diagram illustrating a digital configuration example.

FIG. 26 is a circuit diagram of a part thereof.

FIG. 27 is a different partial circuit diagram.

[Explanation of symbols]

 20 signal processing means 26a, 26b memories 27a, 27b logical product calculating means 28a, 28b first logical calculating means 33a, 33b logical sum calculating means 34 second logical calculating means 45 coupling coefficient varying means

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Shuji Motomura 1-3-6 Nakamagome, Ota-ku, Tokyo Within Ricoh Co., Ltd.

Claims (3)

[Claims] 1. A memory for holding a set of two coupling coefficients of excitatory coupling and inhibitory coupling for a plurality of input signals, and a logic for calculating a logical product of the input signal and each coupling coefficient. The product operation means, the first logic operation means for performing the logic operation of the operation results by these logic product operation means in the same group, and the operation results by these first logic operation means are the excitatory coupling group and the inhibitory coupling group. Signal processing means having a logical sum operation means for performing a logical sum operation in each group and a second operation means for performing an logical operation of the operation result of these logical sum operation means and obtaining an output signal. A signal processing device provided. 2. The signal processing device according to claim 1, wherein the signal processing means has a coupling coefficient varying means for varying each coupling coefficient stored in the memory. 3. The signal processing device according to claim 1, wherein a plurality of signal processing means are connected in a mesh.