Qualcomm incorporated (20240095493). DESPARSIFIED CONVOLUTION FOR SPARSE TENSORS simplified abstract
Contents
- 1 DESPARSIFIED CONVOLUTION FOR SPARSE TENSORS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DESPARSIFIED CONVOLUTION FOR SPARSE TENSORS - 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
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
DESPARSIFIED CONVOLUTION FOR SPARSE TENSORS
Organization Name
Inventor(s)
Jamie Menjay Lin of San Diego CA (US)
Jian Shen of San Diego CA (US)
DESPARSIFIED CONVOLUTION FOR SPARSE TENSORS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240095493 titled 'DESPARSIFIED CONVOLUTION FOR SPARSE TENSORS
Simplified Explanation
The present disclosure provides techniques for desparsified convolution in a convolutional neural network. A weight tensor with unstructured sparsity is accessed, and a densified weight tensor is generated by directionally squeezing the weight tensor to remove sparse values and generating a sparsity map based on the directional squeezing. The densified weight tensor and sparsity map are output for use in a convolutional neural network.
- Weight tensor with unstructured sparsity is accessed
- Densified weight tensor is generated by directionally squeezing the weight tensor
- Sparsity map is generated based on the directional squeezing
- Densified weight tensor and sparsity map are output for use in a convolutional neural network
Potential Applications
This technology can be applied in various fields such as image recognition, natural language processing, and signal processing.
Problems Solved
This technology helps in improving the efficiency and accuracy of convolutional neural networks by reducing sparsity in weight tensors.
Benefits
The benefits of this technology include enhanced performance of convolutional neural networks, improved training speed, and better utilization of computational resources.
Potential Commercial Applications
One potential commercial application of this technology is in developing advanced computer vision systems for autonomous vehicles.
Possible Prior Art
One possible prior art could be techniques for sparsity optimization in neural networks using pruning algorithms.
Unanswered Questions
How does this technology compare to existing methods for desparsified convolution?
This article does not provide a direct comparison with existing methods for desparsified convolution.
What are the limitations of this technology in real-world applications?
This article does not discuss the potential limitations of implementing this technology in real-world applications.
Original Abstract Submitted
certain aspects of the present disclosure provide techniques for desparsified convolution. a weight tensor having unstructured sparsity is accessed, and a densified weight tensor is generated based on the weight tensor by directionally squeezing the weight tensor to remove sparse values, and generating a sparsity map based on the directional squeezing. the densified weight tensor and sparsity map are output for use in a convolutional neural network.