Abstract: Methods and apparatus for reducing a size of a neural network model, the method including: compressing data of the neural network model; identifying structure information of a vector register, wherein the structure information includes a number of registers included in the vector register; comparing a number of elements in the compressed data with a first condition, wherein the first condition is determined based on the number of registers in the vector register; and in response to the number of elements satisfying the first condition, associating the compressed data with the vector register to enable loading the compressed data to the vector register.

Abstract: A display substrate, a method for manufacturing the same, and a display device are provided.

Abstract: Disclosed are an array substrate, a display panel and a display apparatus. The array substrate includes: gate lines, data lines, and pixel units. The gate lines and the data lines are arranged between at least part of the adjacent pixel units. The array substrate further includes: common electrode lead wires and common electrode layers. The common electrode lead wires are arranged on a same layer as the data lines, extend in a same direction as the data lines, and are located between at least part of the adjacent pixel units. The common electrode layers are insulated from the common electrode lead wires through insulating layers and are connected with the common electrode lead wires through via holes in the insulating layers. The via holes are located in a region where the gate lines and the common electrode lead wires intersect.

Abstract: Methods and devices, the method including receiving a matrix of a neural network model; classifying at least a portion of the matrix as a first section based on a first distribution pattern of non-zero elements of the portion of the matrix; and identifying memory addresses of the non-zero elements in the first section of the matrix for loading, according to a first order determined based on the first distribution pattern, the non-zero elements in the first section into one or more vector registers.

Abstract: Methods and apparatus for reducing a size of a neural network model, the method including: compressing data of the neural network model; identifying structure information of a vector register, wherein the structure information includes a number of registers included in the vector register; comparing a number of elements in the compressed data with a first condition, wherein the first condition is determined based on the number of registers in the vector register; and in response to the number of elements satisfying the first condition, associating the compressed data with the vector register to enable loading the compressed data to the vector register.

Abstract: A system and methods are provided for image driven quality control for array based PCR. The system comprises a PCR unit, a reaction array plate, a convolutional neural network (CNN) configured to receive a sequence of images of the reaction array plate in the PCR system, and an output of the CNN coupled to a control for the reaction array plate. The method comprises applying a sequence of images from a plurality of subarrays of the reaction array plate to a plurality of CNNs during operation of the PCR system on the reaction plate array, operating the CNNs to generate failure mode predictions for the reaction plate based on the sequence of images, and coupling an output of the CNNs to one or more of a setting for manufacture of the reaction array plate or to control the PCR system.

Abstract: Disclosed are a soft solvent-free flame-retardant polyurethane synthetic leather and a preparation method therefor. The soft solvent-free flame-retardant polyurethane synthetic leather comprises an antifouling layer, a surface layer, an intermediate layer, a bonding layer and a base cloth in sequence from top to bottom, wherein the bonding layer is prepared from component A and an isocyanate; the molar ratio of —NCO in the isocyanate to —OH in the component A is 0.85-0.93; and the component A is composed of a polyhydric alcohol, an inhibition-type catalyst, a flame retardant, a filler and a viscosity modifier in parts by weight.

Abstract: Disclosed are a soft solvent-free flame-retardant polyurethane synthetic leather and a preparation method therefor. The soft solvent-free flame-retardant polyurethane synthetic leather comprises an antifouling layer, a surface layer, an intermediate layer, a bonding layer and a base cloth in sequence from top to bottom, wherein the bonding layer is prepared from component A and an isocyanate; the molar ratio of —NCO in the isocyanate to —OH in the component A is 0.85-0.93; and the component A is composed of a polyhydric alcohol, an inhibition-type catalyst, a flame retardant, a filler and a viscosity modifier in parts by weight. Disclosed are a soft solvent-free flame-retardant polyurethane synthetic leather and a preparation method therefor.

Abstract: A system and methods are provided for image driven quality control for array based PCR. The system comprises a PCR unit, a reaction array plate, a convolutional neural network (CNN) configured to receive a sequence of images of the reaction array plate in the PCR system, and an output of the CNN coupled to a control for the reaction array plate. The method comprises applying a sequence of images from a plurality of subarrays of the reaction array plate to a plurality of CNNs during operation of the PCR system on the reaction plate array, operating the CNNs to generate failure mode predictions for the reaction plate based on the sequence of images, and coupling an output of the CNNs to one or more of a setting for manufacture of the reaction array plate or to control the PCR system.

Abstract: A Mobile Agent (MA), a Radio Access Network (RAN), and a network adaptation method are disclosed herein. The MA is connected to an access layer of an air interface protocol stack for a first network and an access layer of a Core Network (CN) interface protocol stack for a second network to adapt and forward signaling messages and data sent by a Mobile Station (MS) of the first network and a CN of the second network. In the network evolution process, the MA achieves backward compatibility of the MS and the network, and enables smooth evolution.

Abstract: A Mobile Agent (MA), a Radio Access Network (RAN), and a network adaptation method are disclosed herein. The MA is connected to an access layer of an air interface protocol stack for a first network and an access layer of a Core Network (CN) interface protocol stack for a second network to adapt and forward signaling messages and data sent by a Mobile Station (MS) of the first network and a CN of the second network. In the network evolution process, the MA achieves backward compatibility of the MS and the network, and enables smooth evolution.