18320745. HARDWARE FRIENDLY MULTI-KERNEL CONVOLUTION NETWORK simplified abstract (Samsung Electronics Co., Ltd.)
Contents
- 1 HARDWARE FRIENDLY MULTI-KERNEL CONVOLUTION NETWORK
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 HARDWARE FRIENDLY MULTI-KERNEL CONVOLUTION NETWORK - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.9.1 Unanswered Questions
- 1.9.2 How does the hardware-friendly multi-kernel convolution block compare to traditional convolutional neural networks in terms of computational efficiency and performance?
- 1.9.3 What specific industries or applications could benefit the most from implementing the hardware-friendly multi-kernel convolution block technology?
- 1.10 Original Abstract Submitted
HARDWARE FRIENDLY MULTI-KERNEL CONVOLUTION NETWORK
Organization Name
Inventor(s)
Qingfeng Liu of San Diego CA (US)
Mostafa El-khamy of San Diego CA (US)
Sukhwan Lim of Los Altos Hills CA (US)
HARDWARE FRIENDLY MULTI-KERNEL CONVOLUTION NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 18320745 titled 'HARDWARE FRIENDLY MULTI-KERNEL CONVOLUTION NETWORK
Simplified Explanation
The abstract describes a system and method for processing and combining feature maps using a hardware-friendly multi-kernel convolution block (HFMCB). The method involves splitting an input feature map into multiple feature maps with reduced channels, processing each with different kernels, and then combining the processed feature maps.
- The system and method involve splitting an input feature map into multiple feature maps with reduced channels.
- Each of the feature maps is processed with a different series of kernels.
- The processed feature maps are then combined to produce the final output.
Potential Applications
This technology could be applied in image recognition systems, video processing, and other machine learning tasks that involve processing and combining feature maps efficiently.
Problems Solved
1. Efficient processing of feature maps with reduced channels. 2. Hardware-friendly implementation of multi-kernel convolution blocks.
Benefits
1. Improved performance in processing feature maps. 2. Reduced computational complexity. 3. Enhanced efficiency in combining feature maps.
Potential Commercial Applications
Optimizing image recognition algorithms, enhancing video processing systems, improving machine learning models for various applications.
Possible Prior Art
One possible prior art could be the use of traditional convolutional neural networks for processing feature maps, which may not be as hardware-friendly or efficient as the HFMCB described in the patent application.
Unanswered Questions
How does the hardware-friendly multi-kernel convolution block compare to traditional convolutional neural networks in terms of computational efficiency and performance?
The article does not provide a direct comparison between the HFMCB and traditional convolutional neural networks in terms of computational efficiency and performance.
What specific industries or applications could benefit the most from implementing the hardware-friendly multi-kernel convolution block technology?
The article does not specify which industries or applications could benefit the most from implementing the HFMCB technology.
Original Abstract Submitted
A system and a method are disclosed for processing and combining feature maps using a hardware friendly multi-kernel convolution block (HFMCB). The method including splitting an input feature map into a plurality of feature maps, each of the plurality of feature maps having a reduced number of channels; processing each of the plurality of feature maps with a different series of kernels; and combining the processed plurality of feature maps.
