Abstract:
A recognition apparatus and a training method are provided. The recognition apparatus includes a memory configured to store a neural network including a previous layer of neurons, and a current layer of neurons that are activated based on first synaptic signals and second synaptic signals, the first synaptic signals being input from the previous layer, and the second synaptic signals being input from the current layer. The recognition apparatus further includes a processor configured to generate a recognition result based on the neural network. An activation neuron among the neurons of the current layer generates a first synaptic signal to excite or inhibit neurons of a next layer, and generates a second synaptic signal to inhibit neurons other than the activation neuron in the current layer.
Abstract:
A method and apparatus for processing data are provided. The processor includes an input buffer, a data extractor, a multiplier, and an adder. The input buffer receives data and stores the data. The data extractor extracts kernel data corresponding to a kernel in the data from the input buffer. The multiplier multiplies the extracted kernel data by a convolution coefficient. The adder calculates a sum of multiplication results from the multiplier.
Abstract:
A method of extracting a static pattern from an output of an event-based sensor. The method may include receiving an event signal from the event-based sensor in response to dynamic input, and extracting a static pattern associated with the dynamic input based on an identifier and time included in the event signal. The static pattern may be extracted from a map generated based on the identifier and time.
Abstract:
A method and apparatus for analyzing a motion based on depth information are provided. The method includes: receiving event signals from a first vision sensor configured to generate at least one event signal by sensing at least a portion of an object in which a motion occurs; receiving a current frame from a second vision sensor configured to time-synchronously capture the object; synchronizing the received event signals and the received current frame; and obtaining depth information of the object based on the synchronized event signals and current frame.
Abstract:
An apparatus and method for analyzing an image including event information for determining a pattern of at least one pixel group corresponding to event information included in an input image, and analyzes at least one of an appearance of an object and a motion of the object, based on the at least one pattern.
Abstract:
Disclosed is an image adjustment apparatus including a receiver which is configured to receive a first input image of an object which is time-synchronously captured and a second input image in which a motion event of the object is sensed time-asynchronously, and an adjuster which is configured to adjust the first input image and the second input image.
Abstract:
A motion recognizing apparatus and method are provided. According to an aspect, a motion recognizing apparatus may include: an optical sensor configured to sense at least a portion of a subject where a motion occurs and to output one or more events in response thereto; a motion tracing unit configured to trace a motion locus of the portion where the motion occurs based on the one or more outputted events; and a motion pattern determining unit configured to determine a motion pattern of the portion where the motion occurs based on the traced motion locus.
Abstract:
A method and device for predicting an anomaly in a manufacturing process. The method includes receiving time-series equipment data including one or both of sensor data and specification data, converting the time-series equipment data into an image, dividing the image into a plurality of patch images, outputting a probability for each class associated with a sign of an anomaly in the time-series equipment data by inputting the plurality of patch images to a pretrained artificial neural network (ANN), and predicting the sign of the anomaly in the time-series equipment data by adjusting a probability weight for each class based on a preset standard.
Abstract:
A method and device for predicting a defect. The method includes determining a sequence between a plurality of sub-models by modeling a production process into the plurality of sub-models, mapping production process data into each of the plurality of sub-models, determining, by a corresponding sub-model, output data comprising defect information on a potential defect occurring in a corresponding step, for each of the plurality of sub-models, predicting information associated with a defect in the production process based on the output data corresponding to each of the plurality of sub-models, and inputting the output data of each of the sub-models to a subsequent sub-model of the corresponding sub-model, based on the sequence.
Abstract:
A method for operating an artificial neuron and an apparatus for performing the method are provided. The artificial neuron may calculate a change amount of an activation based on an input signal received via an input synapse, determine whether an event occurs in response to the calculated change amount of the activation, and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event.