A Survey of Quantization Methods for Efficient Neural Network Inference [PDF]
Low-Power Computer Vision, 2021 As soon as abstract mathematical computations were adapted to computation on digital computers, the problem of efficient representation, manipulation, and communication of the numerical values in those computations arose.
A. Gholami +5 more
semanticscholar +1 more source
Accurate prediction of protein structures and interactions using a 3-track neural network
Science, 2021 Deep learning takes on protein folding In 1972, Anfinsen won a Nobel prize for demonstrating a connection between a protein's amino acid sequence and its three-dimensional structure.
Baek M +31 more
semanticscholar +1 more source
Instant neural graphics primitives with a multiresolution hash encoding [PDF]
ACM Transactions on Graphics, 2022 Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus ...
T. Müller +3 more
semanticscholar +1 more source
Unet-Astar: A Deep Learning-Based Fast Routing Algorithm for Unified PCB Routing
IEEE Access, 2023 In recent years, there has been extensive research on the routing problem of printed circuit boards (PCBs). Due to the increasing number of pins, high pin density, and unique physical constraints, manual PCB routing has become a time-consuming task to ...
Shiyuan Yin +5 more
doaj +1 more source
Reinforcement-learning-based parameter adaptation method for particle swarm optimization
Complex & Intelligent Systems, 2023 Particle swarm optimization (PSO) is a well-known optimization algorithm that shows good performances in solving different optimization problems. However, the PSO usually suffers from slow convergence.
Shiyuan Yin +6 more
doaj +1 more source
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network [PDF]
Computer Vision and Pattern Recognition, 2016 Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled
Wenzhe Shi +7 more
semanticscholar +1 more source
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs).
Xiangyu Zhang +3 more
semanticscholar +1 more source
International Journal of Advanced Robotic Systems, 2021 As a fundamental assumption in simultaneous localization and mapping, the static scenes hypothesis can be hardly fulfilled in applications of indoor/outdoor navigation or localization.
Yujia Zhai +4 more
doaj +1 more source
Prediction model of coal seam gas content based on ACSOA optimized BP neural network
Meikuang Anquan, 2022 For the problem of coal seam gas content prediction, the influencing factors of coal seam gas content were analyzed by taking No.2 coal seam of Chensilou Coal Mine as the research object.
Prediction model of coal seam gas content based on ACSOA optimized BP neural network
doaj +1 more source
EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces [PDF]
Journal of Neural Engineering, 2016 Objective. Brain–computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI
Vernon J. Lawhern +5 more
semanticscholar +1 more source