Results 261 to 270 of about 1,721,209 (309)
Some of the next articles are maybe not open access.
MeliusNet: An Improved Network Architecture for Binary Neural Networks
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2021Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices with limited ...
Joseph Bethge +4 more
semanticscholar +1 more source
On the Application of Binary Neural Networks in Oblivious Inference
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021This paper explores the application of Binary Neural Networks (BNN) in oblivious inference, a service provided by a server to mistrusting clients. Using this service, a client can obtain the inference result on her data by a trained model held by the ...
Mohammad Samragh +4 more
semanticscholar +1 more source
Tree-Structured Binary Neural Networks
2021 29th Signal Processing and Communications Applications Conference (SIU), 2021Deep Neural Networks are resource-intensive learning models. To enable their training and deployment on low-end devices, decreasing their computational requirements has become an attractive research area in recent years. One of the most promising approaches in this field is designing networks which use only binary values for the network weights and ...
Ayse Serbetci, Yusuf Sinan Akgul
openaire +1 more source
Modulated Binary Clique Convolutional Neural Network
2019 Seventh International Conference on Advanced Cloud and Big Data (CBD), 2019Although Convolutional Neural Networks (CNNs) achieve effectiveness in various computer vision tasks, the significant requirement of storage of such networks hinders the deployment on computationally limited devices. In this paper, we propose a new compact and portable deep learning network named Modulated Binary Clique Convolutional Neural Network ...
Xia, J. +6 more
openaire +2 more sources
Enabling On-device Continual Learning with Binary Neural Networks
VISIGRAPP : VISAPPOn-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities.
Lorenzo Vorabbi +3 more
semanticscholar +1 more source
Cascade neural network for binary mapping
IEEE Transactions on Neural Networks, 1993The problem of choosing a suitable number of neurons for a neural network which realizes any given binary mapping is automatically solved by the proposed cascade architecture. The utilized algorithm, based on linear programming, the complexity of the resulting net, and its generalization capability are discussed.
MARTINELLI, Giuseppe +2 more
openaire +2 more sources
2020
Convolutional neural networks (CNNs) are used in a spread spectrum of machine learning applications, such as computer vision and speech recognition. Computation and memory accesses are the major challenges for the deployment of CNNs in resource -limited and low -power embedded systems.
openaire +1 more source
Convolutional neural networks (CNNs) are used in a spread spectrum of machine learning applications, such as computer vision and speech recognition. Computation and memory accesses are the major challenges for the deployment of CNNs in resource -limited and low -power embedded systems.
openaire +1 more source
International Conference on Information Photonics, 2020
In this work, we present a hardware-efficient architecture for pedestrian detection with neuromorphic Dynamic Vision Sensors (DVSs), asynchronous camera sensors that report discrete changes in light intensity.
Fernando Cladera Ojeda +4 more
semanticscholar +1 more source
In this work, we present a hardware-efficient architecture for pedestrian detection with neuromorphic Dynamic Vision Sensors (DVSs), asynchronous camera sensors that report discrete changes in light intensity.
Fernando Cladera Ojeda +4 more
semanticscholar +1 more source
PXNOR: Perturbative Binary Neural Network
2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet), 2019Research into deep neural networks has brought about architectures and models that solve problems we once thought could not be approached by machine learning. Year after year, performance improves, to the point that it is becoming difficult to differentiate between the strengths of deep neural network models given our current data sets. However, due to
Vlad Pelin, Ion Emilian Radoi
openaire +1 more source
From Quantitative Analysis to Synthesis of Efficient Binary Neural Networks
International Conference on Machine Learning and Applications, 2020Binary Neural Networks (BNNs) offer an effective way to slash the cost of computation and memory accesses in inference. Recently, a plurality of ideas has been proposed, some of which are complementary while others are incompatible.
Tim Stadtmann +2 more
semanticscholar +1 more source