Abstract: Provided are a signal readout circuit and a method therefor. In the signal readout circuit, a readout row selector is configured to gate a row of pixel units in a pixel array. A reset row selector is configured to gate first reset switches of the row of pixel units. Each pixel unit in the row in a pixel subarray included in the pixel array converts an optical signal into an electrical signal, and outputs the electrical signal to a connected pixel subarray readout feedback circuit. When it is determined based on the electrical signal that a signal generation condition is met, a reset signal is generated and sent to a first pixel unit, and an output signal is generated for output.

Abstract: A spiking convolutional neural network based on a FLASH storage and computing array, including: a sampling module, a FLASH-based storage and computing array and a corresponding neuron module, and a counter module; the sampling module is used to sample an input image to obtain an input spike; the FLASH-based storage and computing array stores a weight matrix, and is used to perform a vector matrix multiplying operation on the input spike and the weight matrix, and an operation result is output in a form of current; the neuron module is used to integrate the operation result of the FLASH-based storage and computing array so as to generate an output spike; the counter module is used to count a number of spikes generated by the neuron module of an output layer, and determine the number of spikes of the neuron module with a largest number of spikes as a recognition result.

Abstract: An encoding method for a light signal, an electronic device, a non-transitory computer-readable storage medium, and a light signal detection circuit are provided. The encoding method for a light signal includes: detecting whether there is a change in a light intensity signal representing a light intensity, the light intensity signal being converted by a photosensitive unit from a received photon stream; encoding, in response to detecting a change in the light intensity signal, the changed light intensity signal to obtain an encoding result; and arranging the encoding result into an encoded sequence according to a time sequence relationship corresponding to changes in the light intensity, the encoded sequence representing time sequence code of the photon stream, and the time sequence relationship representing an order of the changes in the light intensity within a time period.

Abstract: A system and a method for compressing an image based on a FLASH in-memory computing array are provided. The system includes: a convolutional neural network for encoding of the FLASH in-memory computing array, a convolutional neural network for decoding based on the FLASH in-memory computing array, and a quantization module; the convolutional neural network for encoding based on the FLASH in-memory computing array is configured to encode an original image to obtain a feature image; the quantization module is configured to quantize the feature image to obtain a quantized image; the convolutional neural network for decoding based on the FLASH in-memory computing array is configured to decode the quantized image to obtain a compressed image.

Abstract: Provided are a signal readout circuit and a method therefor. In the signal readout circuit, a readout row selector is configured to gate a row of pixel units in a pixel array. A reset row selector is configured to gate first reset switches of the row of pixel units. Each pixel unit in the row in a pixel subarray included in the pixel array converts an optical signal into an electrical signal, and outputs the electrical signal to a connected pixel subarray readout feedback circuit. When it is determined based on the electrical signal that a signal generation condition is met, a reset signal is generated and sent to a first pixel unit, and an output signal is generated for output.

Abstract: A method, computer system, and a computer-readable medium for registering one or more structures to a desired orientation for planning and guidance for surgery is provided. The method includes in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique; in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations; in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.

Abstract: A spiking convolutional neural network based on a FLASH storage and computing array, including: a sampling module, a FLASH-based storage and computing array and a corresponding neuron module, and a counter module; the sampling module is used to sample an input image to obtain an input spike; the FLASH-based storage and computing array stores a weight matrix, and is used to perform a vector matrix multiplying operation on the input spike and the weight matrix, and an operation result is output in a form of current; the neuron module is used to integrate the operation result of the FLASH-based storage and computing array so as to generate an output spike; the counter module is used to count a number of spikes generated by the neuron module of an output layer, and determine the number of spikes of the neuron module with a largest number of spikes as a recognition result.

Abstract: A system and a method for compressing an image based on a FLASH in-memory computing array are provided. The system includes: a convolutional neural network for encoding of the FLASH in-memory computing array, a convolutional neural network for decoding based on the FLASH in-memory computing array, and a quantization module; the convolutional neural network for encoding based on the FLASH in-memory computing array is configured to encode an original image to obtain a feature image; the quantization module is configured to quantize the feature image to obtain a quantized image; the convolutional neural network for decoding based on the FLASH in-memory computing array is configured to decode the quantized image to obtain a compressed image.

Abstract: The present disclosure relates to the field of semiconductor integrated circuits and manufacturing technologies thereof, and discloses a method and device for realizing a convolution operation based on an NOR flash storage structure. The NOR flash array has a structure of an array composed of a plurality of NOR flash cells. The convolution operation method includes: storing elements of a convolution kernel matrix into the NOR flash cells; converting elements of an input matrix into voltages and applying the voltages to gate terminals of the NOR flash cells; applying a driving voltage to source terminals of the NOR flash cells; and collecting, via drain terminals of the NOR flash cells, current values of each column to obtain a convolution operation result.

Abstract: The present disclosure relates to the field of semiconductor integrated circuits and manufacturing technologies thereof, and discloses a method and device for realizing a convolution operation based on an NOR flash storage structure. The NOR flash array has a structure of an array composed of a plurality of NOR flash cells. The convolution operation method includes: storing elements of a convolution kernel matrix into the NOR flash cells; converting elements of an input matrix into voltages and applying the voltages to gate terminals of the NOR flash cells; applying a driving voltage to source terminals of the NOR flash cells; and collecting, via drain terminals of the NOR flash cells, current values of each column to obtain a convolution operation result.

Abstract: A method, computer system, and a computer-readable medium for registering one or more structures to a desired orientation for planning and guidance for surgery is provided. The method includes in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique; in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations; in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.