Abstract: A method of performing convolution in a neural network with variable dilation rate is provided. The method includes receiving a size of a first kernel and a dilation rate, determining at least one of size of one or more disintegrated kernels based on the size of the first kernel, a baseline architecture of a memory and the dilation rate, determining an address of one or more blocks of an input image based on the dilation rate, and one or more parameters associated with a size of the input image and the memory. Thereafter, the one or more blocks of the input image and the one or more disintegrated kernels are fetched from the memory, and an output image is obtained based on convolution of each of the one or more disintegrated kernels and the one or more blocks of the input image.

Abstract: A method of performing convolution in a neural network with variable dilation rate is provided. The method includes receiving a size of a first kernel and a dilation rate, determining at least one of size of one or more disintegrated kernels based on the size of the first kernel, a baseline architecture of a memory and the dilation rate, determining an address of one or more blocks of an input image based on the dilation rate, and one or more parameters associated with a size of the input image and the memory. Thereafter, the one or more blocks of the input image and the one or more disintegrated kernels are fetched from the memory, and an output image is obtained based on convolution of each of the one or more disintegrated kernels and the one or more blocks of the input image.

Abstract: A method of performing convolution in a neural network with variable dilation rate is provided. The method includes receiving a size of a first kernel and a dilation rate, determining at least one of size of one or more disintegrated kernels based on the size of the first kernel, a baseline architecture of a memory and the dilation rate, determining an address of one or more blocks of an input image based on the dilation rate, and one or more parameters associated with a size of the input image and the memory. Thereafter, the one or more blocks of the input image and the one or more disintegrated kernels are fetched from the memory, and an output image is obtained based on convolution of each of the one or more disintegrated kernels and the one or more blocks of the input image.

Abstract: A method of performing convolution in a neural network with variable dilation rate is provided. The method includes receiving a size of a first kernel and a dilation rate, determining at least one of size of one or more disintegrated kernels based on the size of the first kernel, a baseline architecture of a memory and the dilation rate, determining an address of one or more blocks of an input image based on the dilation rate, and one or more parameters associated with a size of the input image and the memory. Thereafter, the one or more blocks of the input image and the one or more disintegrated kernels are fetched from the memory, and an output image is obtained based on convolution of each of the one or more disintegrated kernels and the one or more blocks of the input image.

Abstract: A novel chimeric protein of rabies virus designed to express a chimeric G protein at a high level in transgenic plants. A gene was also designed and chemically synthesised to encode the chimeric G protein and expressed at high level in plant tissue. The gene was expressed in transgenic tobacco plants to examine its therapeutic efficacy against infection by rabies virus. The chimeric G protein was enriched in plant membranes. The BalbC mice were immunised with the plant leaf expressed G-protein. Plant derived chimeric G protein elicited higher immune response as compared to the commercial vaccine. The mice displayed protective immunity when they were challenged with live virus. Chimeric G protein expressed at high level in plant leaves was demonstrated to function as a commercially valuable subunit vaccine against rabies virus infection.

Abstract: A novel chimeric protein of rabies virus designed to express a chimeric G protein at a high level in transgenic plants. A gene was also designed and chemically synthesised to encode the chimeric G protein and expressed at high level in plant tissue. The gene was expressed in transgenic tobacco plants to examine its therapeutic efficacy against infection by rabies virus. The chimeric G protein was enriched in plant membranes. The BalbC mice were immunised with the plant leaf expressed G-protein. Plant derived chimeric G protein elicited higher immune response as compared to the commercial vaccine. The mice displayed protective immunity when they were challenged with live virus. Chimeric G protein expressed at high level in plant leaves was demonstrated to function as a commercially valuable subunit vaccine against rabies virus infection.