Average biased ReLU based CNN descriptor for improved face retrieval
SR Dubey, S Chakraborty - Multimedia Tools and Applications, 2021 - Springer
The convolutional neural networks (CNN), including AlexNet, GoogleNet, VGGNet, etc.
extract features for many computer vision problems which are very discriminative. The …
extract features for many computer vision problems which are very discriminative. The …
Functional networks and applications: A survey
G Zhou, Y Zhou, H Huang, Z Tang - Neurocomputing, 2019 - Elsevier
Functional networks (FNs) are extensions of neural networks (NNs). Unlike NNs, FNs
considers general functional models instead of sigmoid-like models. Additionally, in FNs …
considers general functional models instead of sigmoid-like models. Additionally, in FNs …
Comparison of machine learning approaches for classification of invoices
A Khan - 2020 - trepo.tuni.fi
Machine learning has become one of the leading sciences governing modern world.
Various disciplines specifically neural networks have recently gained a lot of attention due to …
Various disciplines specifically neural networks have recently gained a lot of attention due to …
Quantization and inferencing for low-bitwidth neural networks
JM Lin, EC Park, N Kwak - US Patent 11,449,758, 2022 - Google Patents
A method for operating a low-bitwidth neural network includes converting a first activation to
a non-negative value (eg, absolute value). The first activation has a signed value. The sign …
a non-negative value (eg, absolute value). The first activation has a signed value. The sign …