Abstract: A small-sized pen-shaped input apparatus precisely detects handwriting input. The apparatus compensates for the effects of the inclination of the pen-shaped input apparatus. An initial inclination angle calculating section calculates the initial value of the inclination angle of a pen shaft in a gravity coordinate system. The inclination angle variation calculating section calculates a variation value of the inclination angle of the pen shaft. A handwriting inclination angle calculating section calculates the inclination angle of the pen shaft when writing. A coordinates conversion calculating section converts the coordinate system of the acceleration from the pen shaft coordinate system to the gravity coordinate system. A movement amount calculating section calculates the movement direction and the movement distance of the pen's tip end. Finally, a handwriting detecting section detects a state of handwriting or non-handwriting.

Abstract: A small-sized pen-shaped input apparatus precisely detects handwriting input. The apparatus compensates for the effects of the inclination of the pen-shaped input apparatus. An initial inclination angle calculating section calculates the initial value of the inclination angle of a pen shaft in a gravity coordinate system. The inclination angle variation calculating section calculates a variation value of the inclination angle of the pen shaft. A handwriting inclination angle calculating section calculates the inclination angle of the pen shaft when writing. A coordinates conversion calculating section converts the coordinate system of the acceleration from the pen shaft coordinate system to the gravity coordinate system. A movement amount calculating section calculates the movement direction and the movement distance of the pen's tip end. Finally, a handwriting detecting section detects a state of handwriting or non-handwriting.

Abstract: A small-sized pen-shaped input apparatus precisely detects handwriting input. The apparatus compensates for the effects of the inclination of the pen-shaped input apparatus. An initial inclination angle calculating section calculates the initial value of the inclination angle of a pen shaft in a gravity coordinate system. The inclination angle variation calculating section calculates a variation value of the inclination angle of the pen shaft. A handwriting inclination angle calculating section calculates the inclination angle of the pen shaft when writing. A coordinates conversion calculating section converts the coordinate system of the acceleration from the pen shaft coordinate system to the gravity coordinate system. A movement amount calculating section calculates the movement direction and the movement distance of the pen's tip end. Finally, a handwriting detecting section detects a state of handwriting or non-handwriting.

Abstract: 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.

Abstract: A signal processing apparatus has a circuit network which is formed by connecting a plurality of neuron units into a network, each of the neuron being provided with a self-learning means having a weight function varying means and a weight function generating means for generating a variable weight function of the weight function varying means, on the basis of a positive or negative error signal obtained as a result of the comparison between an output signal and a teaching signal. In order to obtain a positive error signal .delta..sub.j(+) and a negative error signal .delta..sub.j(-), there is provided a differential coefficient calculating means for calculating two kinds of differential coefficients for a neuron response function, the calculation being done on the basis of the output signal from the neuron unit.

Abstract: 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.

Abstract: A neuron unit includes first shift registers for storing first weighting coefficients; second shift registers for storing second weighting coefficients; a first gate circuit for obtaining first logical products of first binary input signals and the first weighting coefficients; a second gate circuit for obtaining second logical products of second binary input signals and the second weighting coefficients; a third gate circuit for obtaining a logical sum of the first logical products, and for outputting a first binary response signal corresponding to the logical sum; a fourth gate circuit for obtaining a logical sum of the second logical products, and for outputting a second binary response signal corresponding to the logical sum; a signal generator for outputting a binary signal; and an output circuit for outputting a binary output signal, the first binary response signal being used as the binary output signal when values of the first and second binary response signals differ from each other, and the binary s

Abstract: 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.

Abstract: A neuron unit simultaneously processes a plurality of binary input signals.

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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method and apparatus are disclosed that modify [ies] and generalize [s] the use in artificial neural networks of the error backpropagation algorithm. Each neuron unit first divides a plurality of weighted inputs into more than one group, then sums up weighted inputs in each group to provide each group's intermediate outputs, and finally processes the intermediate outputs to produce an output of the neuron unit. Since the method uses, when modifying each weight, a partial differential coefficient generated by partially-differentiating the output of the neuron unit by each weighted input, the weight can be properly modified even if the output of a neuron unit as a function of intermediate outputs has a plurality of variables corresponding to the number of groups.

Abstract: A neuron unit includes first shift registers for storing first weighting coefficients; second shift registers for storing second weighting coefficients; a first gate circuit for obtaining first logical products of first binary input signals and the first weighting coefficients; a second gate circuit for obtaining second logical products of second binary input signals and the second weighting coefficients; a third gate circuit for obtaining a logical sum of the first logical products, and for outputting a first binary response signal corresponding to the logical sum; a fourth gate circuit for obtaining a logical sum of the second logical products, and for outputting a second binary response signal corresponding to the logical sum; a signal generator for outputting a binary signal; and an output circuit for outputting a binary output signal, the first binary response signal being used as the binary output signal when values of the first and second binary response signals differ from each other, and the binary s

Abstract: A method for identifying the presence or absence of an aggregation of particles distributed on a translucent surface includes the steps of providing a light sensing device for sensing light incident thereon and producing an output value which represents the intensity of the incident light, and identifying a first output value which is produced by the light sensing device when there is no light incident thereon. The method also identifies a second output value which is produced by the light sensing means when, with no particles present on the translucent surface, light is directed through the translucent surface onto the light sensing device. With a distribution of particles deposited on the translucent surface, light is directed through the translucent surface and onto the light sensing device, causing the light sensing device to produce a third output value. A final output value is then determined as a function of said first, second and third output values.

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.

Abstract: An aggregation pattern detecting apparatus includes a microplate having a plurality of reactive vessels in which aggregation patterns are formed, a light source arranged above the microplate, and a light sensor arrangement positioned below the microplate. The microplate is removably fastened to a main body, and a movable frame is movably supported on the main body. The light source and light sensor arrangement are carried on the movable frame for movement therewith. A driving mechanism effects movement of the movable frame and is controlled by a main control section. A reference plate is provided separately from the microplate, and has a plurality of through holes therein which correspond to the reactive vessels of the microplate. The reference plate is removably fastenable to the main body at the normal operative position of the microplate.

Abstract: A method and apparatus for discriminating aggregation patterns includes detection of an image of the aggregation pattern and dividing the image into a plurality of image line data using a photoelectric element. The image line data defines an image waveform and includes a maximum image value. High and low image levels are defined based on the maximum image value. These high and low image levels are used to determine first and second areas of the aggregation pattern image, which first and second areas respectively include image values at least as large as the high and low image levels. An area difference between the first and second areas and a level difference between the high and low image levels are then calculated, along with a ratio of the area difference to the level difference. The calculated area difference and ratio are then compared with a predetermined reference value to discriminate whether or not the aggregation pattern is positive.

Abstract: An apparatus for discriminating a particle aggregation pattern includes a memory circuit for storing line data output from a CCD line sensor, which line data represents the aggregation pattern. A maximum value is obtained for each set of line data, and thereafter a further maximum value is obtained from the afore-mentioned previously obtained maximum values. A threshold value is determined on the basis of the further maximum value, and is then applied to the line data in order to extract therefrom information regarding the shape and area of the aggregation pattern. In another embodiment, the threshold value is determined on the basis of minimum values obtained from the line data.