Results 51 to 60 of about 1,721,209 (309)
Hardware Platform-Aware Binarized Neural Network Model Optimization
Applied Sciences, 2022 Deep Neural Networks (DNNs) have shown superior accuracy at the expense of high memory and computation requirements. Optimizing DNN models regarding energy and hardware resource requirements is extremely important for applications with resource ...
Quang Hieu Vo +4 more
doaj +1 more source
Neural Distributed Autoassociative Memories: A Survey [PDF]
, 2017 Introduction. Neural network models of autoassociative, distributed memory allow storage and retrieval of many items (vectors) where the number of stored items can exceed the vector dimension (the number of neurons in the network).
Frolov, A. A. +5 more
core +1 more source
Sound event detection with binary neural networks on tightly power-constrained IoT devices [PDF]
International Symposium on Low Power Electronics and Design, 2020 Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on deep neural networks (DNNs) are very effective, but highly demanding in terms of memory, power, and throughput when targeting ultra-low power
G. Cerutti +5 more
semanticscholar +1 more source
Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution [PDF]
Computer Vision and Pattern Recognition, 2020 Binarization of neural network models is considered as one of the promising methods to deploy deep neural network models on resource-constrained environments such as mobile devices.
Hyungjun Kim +3 more
semanticscholar +1 more source
Deep Neural Networks Classification via Binary Error-Detecting Output Codes
Applied Sciences, 2021 One-hot encoding is the prevalent method used in neural networks to represent multi-class categorical data. Its success stems from its ease of use and interpretability as a probability distribution when accompanied by a softmax activation function ...
Martin Klimo +2 more
doaj +1 more source
A high performance k-NN approach using binary neural networks [PDF]
, 2004 This paper evaluates a novel k-nearest neighbour (k-NN) classifier built from binary neural networks. The binary neural approach uses robust encoding to map standard ordinal, categorical and numeric data sets onto a binary neural network.
Austin, J L, Hodge, V J, Lees, K J
core +1 more source
Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments [PDF]
IEEE Transactions on robotics, 2020 Visual place recognition (VPR) is a robot’s ability to determine whether a place was visited before using visual data. While conventional handcrafted methods for VPR fail under extreme environmental appearance changes, those based on convolutional neural
Bruno Ferrarini +3 more
semanticscholar +1 more source
FPGA-based acceleration for binary neural networks in edge computing
Journal of Electronic Science and Technology, 2023 As a core component in intelligent edge computing, deep neural networks (DNNs) will increasingly play a critically important role in addressing the intelligence-related issues in the industry domain, like smart factories and autonomous driving.
Jin-Yu Zhan +6 more
doaj +1 more source
, 2020 Binary Neural Network (BNN) shows its predominance in reducing the complexity of deep neural networks. However, it suffers severe performance degradation. One of the major impediments is the large quantization error between the full-precision weight vector and its binary vector.
Lin, Mingbao +7 more
openaire +2 more sources
A Review of Recent Advances of Binary Neural Networks for Edge Computing [PDF]
IEEE Journal on Miniaturization for Air and Space Systems, 2020 Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains, such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection.
Wenyu Zhao +4 more
semanticscholar +1 more source