Abstract: There is provided with an information processing apparatus. A control unit controls writing of weight data to a first memory and a second memory, and controls readout of the weight data from the first memory and the second memory. The control unit further switches an operation between a first operation in which a processing unit reads out first weight data from the first memory and performs the convolution operation processing using the first weight data while the processing unit writes second weight data to the second memory in parallel, and a second operation in which the processing unit reads out the first weight data from both the first memory and the second memory and performs the convolution operation processing using the first weight data.

Abstract: Provided are a method, an apparatus and a system for training a neural network, and a storage medium storing instructions. The neural network comprises a first neural network and a second neural network, training of the first neural network has not yet completed and training of the second neural network does not start. The method comprises: obtaining a first output by subjecting a sample image to the current first neural network, and obtaining a second output by subjecting the sample image to the current second neural network; and updating the current first neural network according to a first loss function value, and updating the current second neural network according to a second loss function value. The performance of the second neural network can be improved, and the overall training time of the first neural network and the second neural network can be reduced.

Abstract: Disclosures of the present invention describe a halide semiconductor memristor that is suitable for being as an artificial synapse. The halide semiconductor memristor comprises a first electrode layer, an active layer and a second electrode layer, wherein the active layer comprises a first oxide semiconductor film formed on the first electrode layer, a halide semiconductor film formed on the first oxide semiconductor film, and a second oxide semiconductor film formed on the halide semiconductor film Moreover, a variety of experimental data have proved that, this halide semiconductor memristor is indeed suitable for being adopted as a plurality of artificial synapses that are used in manufacture of a neuromorphic device, and exhibits many advantages, including: capable of being driven by a low operation voltage, having a multi-stage adjustable resistance state, and a wide dynamic range of the switching resistance states.

Abstract: Disclosures of the present invention describe a halide semiconductor memristor that is suitable for being as an artificial synapse. The halide semiconductor memristor comprises a first electrode layer, an active layer and a second electrode layer, wherein the active layer comprises a first oxide semiconductor film formed on the first electrode layer, a halide semiconductor film formed on the first oxide semiconductor film, and a second oxide semiconductor film formed on the halide semiconductor film Moreover, a variety of experimental data have proved that, this halide semiconductor memristor is indeed suitable for being adopted as a plurality of artificial synapses that are used in manufacture of a neuromorphic device, and exhibits many advantages, including: capable of being driven by a low operation voltage, having a multi-stage adjustable resistance state, and a wide dynamic range of the switching resistance states.

Abstract: There is provided with an information processing apparatus. A control unit controls writing of weight data to a first memory and a second memory, and controls readout of the weight data from the first memory and the second memory. The control unit further switches an operation between a first operation in which a processing unit reads out first weight data from the first memory and performs the convolution operation processing using the first weight data while the processing unit writes second weight data to the second memory in parallel, and a second operation in which the processing unit reads out the first weight data from both the first memory and the second memory and performs the convolution operation processing using the first weight data.

Abstract: The present disclosure provides a training and application method of a multi-layer neural network model, apparatus and a storage medium. In a forward propagation of the multi-layer neural network model, the number of input feature maps is expanded and a data computation is performed by using the expanded input feature maps.

Abstract: The present disclosure provides a training and application method of a multi-layer neural network model, apparatus and storage medium. A number of channels of a filter in at least one convolutional layer in the multi-layer neural network model is expanded, and a convolution computation is performed by using the filter after expanding the number of channels, so that the performance of the network model does not degrade while simplifying the network model.

Abstract: A training and application method for a neural network model is provided. The training method determines the first network model to be trained and sets a downscaling layer for at least one layer in the first network model, wherein the number of filters and filter kernel of the downscaling layer are identical to those of layers to be trained in the second network model. Filter parameters of the downscaling layer are transmitted to the second network model as training information. By this training method, training can also be performed even when the scale of the layer for training in the first network model is different from that of the layers to be trained in the second network model, and the amount of lost data is small.

Abstract: The present invention provides a novel semiselective medium composition for detecting seed-borne Alternaria brassicicola, which comprises galactose, calcium nitrate, dipotassium hydrogen phosphate, magnesium sulfate, agar, benomyl, and chloramphenicol. The CW medium of the present invention can selectively allow seed-borne Alternaria brassicicola to grow, while effectively suppressing the growth of other seed-borne fungi. Although A. alternata, which is prevalently present on seeds and is similar to A. brassicicola, can still grow on the CW medium, the color of the A. alternata colonies are different from that of A. brassicicola, thus, A. brassicicola can be obviously differentiated.