An end-to-end multi-task object detection using embedded gpu in autonomous driving
Autonomous driving has gained popularity due to its high reliability compared to human
drivers. Autonomous vehicles combine variety of sensors to perceive their surroundings, and …
drivers. Autonomous vehicles combine variety of sensors to perceive their surroundings, and …
Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
M Reiners, K Klamroth, F Heldmann… - Computers & Operations …, 2022 - Elsevier
Overparameterization and overfitting are common concerns when designing and training
deep neural networks, that are often counteracted by pruning and regularization strategies …
deep neural networks, that are often counteracted by pruning and regularization strategies …
Combining multi-view ensemble and surrogate lagrangian relaxation for real-time 3D biomedical image segmentation on the edge
Real-time 3D biomedical image segmentation is always preferred considering the
exponentially growing medical imaging data for the past decade. Recently deep learning …
exponentially growing medical imaging data for the past decade. Recently deep learning …
Rethinking the mechanism of the pattern pruning and the circle importance hypothesis
Network pruning is an effective and widely-used model compression technique. Pattern
pruning is a new sparsity dimension pruning approach whose compression ability has been …
pruning is a new sparsity dimension pruning approach whose compression ability has been …
Hardware-friendly model compression technique of DNN for edge computing
X Liu - 2021 2nd International Conference on Computing and …, 2021 - ieeexplore.ieee.org
The research proposes a design methodology to compress the existing DNN models for low-
cost edge devices. To reduce the computation complexity and memory cost, several novel …
cost edge devices. To reduce the computation complexity and memory cost, several novel …
[PDF][PDF] Efficient and Sparse Neural Networks by Pruning Weights in a Multiobjective Learning Approach
M Reiners, K Klamroth, M Stiglmayr - 2020 - imacm.uni-wuppertal.de
Overparameterization and overfitting are common concerns when designing and training
deep neural networks, that are often counteracted by pruning and regularization strategies …
deep neural networks, that are often counteracted by pruning and regularization strategies …
Methods and devices for irregular pruning for automatic speech recognition
Y Ren, B Li, Y Liu, L Liu - US Patent 12,002,453, 2024 - Google Patents
A method and an apparatus for automatic speech recognition are provided. The method
includes: generating a weight matrix for a layer of a plurality of layers in a neural network; …
includes: generating a weight matrix for a layer of a plurality of layers in a neural network; …