Convolutional neural network (CNN) processing method and apparatus

SON **woo, C Son, HAN JaeJoon… - US Patent 11,514,290, 2022 - Google Patents
2017-12-11 Assigned to SAMSUNG ELECTRONICS CO., LTD. reassignment SAMSUNG
ELECTRONICS CO., LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT …

Method and electronic apparatus for adjusting a neural network

LIN Yu-Hsun, CN Chou, E Chang - US Patent 11,379,716, 2022 - Google Patents
(57) ABSTRACT A method for adjusting a convolutional neural network includes following
operations. The convolutional neural network includes convolution layers in a sequential …

Dynamic pruning of neurons on-the-fly to accelerate neural network inferences

D Gorokhov, A Kozlov - US Patent 12,056,614, 2024 - Google Patents
Abstract Systems, apparatuses and methods may provide for technology that aggregates
contextual information from a first network layer in a neural network having a second …

Computer-implemented methods and systems for dnn weight pruning for real-time execution on mobile devices

Y Wang, X Ma - US Patent App. 17/176,742, 2021 - Google Patents
(52) US Cl. CPC GO6N 3/082 (2013.01); G06K 9/6249 (2013.01); G06N 3/04 (2013.01)(57)
ABSTRACT A computer-implemented method is disclosed for compress ing a deep neural …

Pruning neural networks that include element-wise operations

V Praveen, A Ubale, P Sriram, G Heinrich… - US Patent App. 16 …, 2020 - Google Patents
US20200160185A1 - Pruning neural networks that include element-wise operations - Google
Patents US20200160185A1 - Pruning neural networks that include element-wise operations …

Neuromorphic memory circuit and method of neurogenesis for an artificial neural network

W Yi, C Martin, S Kolouri, P Pilly - US Patent 11,574,679, 2023 - Google Patents
(57) ABSTRACT A memory circuit configured to perform multiply-accumulate (MAC)
operations for performance of an artificial neural network includes a series of synapse cells …

Methods for neural network sparsity channel generation and inference

M Guo - US Patent App. 16/734,268, 2021 - Google Patents
Methods are disclosed for accelerating inference operations of neural network (NN) models
that take advantage of sparse channels. An offline method consolidates sparse channels for …

Low rank matrix compression

T Bar-On, J Subag, Y Fais, J Dreyfuss, G Novik… - US Patent …, 2024 - Google Patents
In an example, an apparatus comprises logic, at least partially including hardware logic, to
implement a lossy compression algorithm which utilizes a data transform and quantization …

Low rank matrix compression

T Bar-On, J Subag, Y Fais, J Dreyfuss, G Novik… - US Patent …, 2023 - Google Patents
H04N19/42—Methods or arrangements for coding, decoding, compressing or
decompressing digital video signals characterised by implementation details or hardware …

Method, apparatus, and electronic device for training place recognition model

D Bai, Y Ling, W Liu - US Patent 12,100,192, 2024 - Google Patents
A computer device extracts local features of sample images based on a first part of a
convolutional neural network (CNN) model. The sample images comprise a plurality of …