Neural network pruning method and system via layerwise analysis
Номер патента: EP4252156A1
Опубликовано: 04-10-2023
Автор(ы): Dongkuan Xu, Enxu Yan, Jiachao LIU
Принадлежит: Moffett International Co Ltd
Опубликовано: 04-10-2023
Автор(ы): Dongkuan Xu, Enxu Yan, Jiachao LIU
Принадлежит: Moffett International Co Ltd
Реферат: Embodiments disclosed herein allowed neural networks to be pruned. The inputs and outputs generated by a reference neural network are used to prune the reference neural network. The pruned neural network may have a subset of the weights that are in the reference neural network.
Quantization method for partial sums of convolution neural network based on computing-in-memory hardware and system thereof
Номер патента: US11423315B2. Автор: Meng-Fan Chang,Ta-Wei Liu,jing-hong Wang. Владелец: National Tsing Hua University NTHU. Дата публикации: 2022-08-23.