Back to results
US 2026/0161330 A1Published application
Machine learning method using pooling on channel attention
AssigneeNovatek Microelectronics Corp.
InventorsChao-Tsung Huang, Yen-Ting Chiu, Yong-Tai Chen
Life of this patent
Estimating the term…
Abstract
A machine learning method using pooling on channel attention includes inputting a first residual input to convolution layers of a first residual network to generate a first convolved output, and inputting the first convolved output to a first pooling layer to generate a first pooling vector. This results in a decrease in both computational time and memory usage, which in turn boosts the efficiency and performance of the machine learning model.
Claims20
A machine learning method using pooling on channel attention, comprising:
- inputting a first residual input to convolution layers of a first residual network to generate a first convolved output;
- and
- inputting the first convolved output to a first pooling layer to generate a first pooling vector.
Dependencies are inferred from the claim text.