Results 71 to 80 of about 1,721,209 (309)

FPGA-Based Memristor Emulator Circuit for Binary Convolutional Neural Networks

IEEE Access, 2020
Binary convolutional neural networks (BCNN) have been proposed in the literature for resource-constrained IoTs nodes and mobile computing devices. Such computing platforms have strict constraints on the power budget, system performance, processing and ...
Mohammed F. Tolba, Yasmin Halawani, Hani Saleh, Baker Mohammad, Mahmoud Al-Qutayri   +4 more
doaj   +1 more source

Design and Development of RNN Anomaly Detection Model for IoT Networks

IEEE Access, 2022
Cybersecurity is important today because of the increasing growth of the Internet of Things (IoT), which has resulted in a variety of attacks on computer systems and networks. Cyber security has become an increasingly difficult issue to manage as various
Imtiaz Ullah, Qusay H. Mahmoud
doaj   +1 more source

Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks

, 2019
Deep neural networks (DNNs) have demonstrated success for many supervised learning tasks, ranging from voice recognition, object detection, to image classification. However, their increasing complexity might yield poor generalization error that make them
AE Hoerl, CM Bishop, H Zou, K Knight, LE Frank, M Rastegari, N Srivastava, PJ Huber, R Tibshirani, VP Nia   +9 more
core   +1 more source

Local Binary Convolutional Neural Networks [PDF]

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN). The design principles of LBC are motivated by local binary patterns (LBP). The LBC layer comprises of a set of fixed sparse pre-defined binary convolutional filters that are not updated during the training process,
Juefei-Xu, Felix, Boddeti, Vishnu Naresh, Savvides, Marios   +2 more
openaire   +2 more sources

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation [PDF]

Computer Vision and Pattern Recognition, 2018
In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically for mobile devices with limited power capacity and computation resources.
Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, I. Reid   +4 more
semanticscholar   +1 more source

Binary Quantization Analysis of Neural Networks Weights on MNIST Dataset

Elektronika ir Elektrotechnika, 2021
This paper considers the design of a binary scalar quantizer of Laplacian source and its application in compressed neural networks. The quantizer performance is investigated in a wide dynamic range of data variances, and for that purpose, we derive novel
Zoran H. Peric, Bojan D. Denic, Milan S. Savic, Nikola J. Vucic, Nikola B. Simic   +4 more
doaj   +1 more source

Structural biology of ferritin nanocages

FEBS Letters, EarlyView.
Ferritin is a conserved iron‐storage protein that sequesters iron as a ferric mineral core within a nanocage, protecting cells from oxidative damage and maintaining iron homeostasis. This review discusses ferritin biology, structure, and function, and highlights recent cryo‐EM studies revealing mechanisms of ferritinophagy, cellular iron uptake, and ...
Eloise Mastrangelo, Flavio Di Pisa
wiley   +1 more source

Feed-Forward Neural Networks Need Inductive Bias to Learn Equality Relations [PDF]

, 2018
Basic binary relations such as equality and inequality are fundamental to relational data structures. Neural networks should learn such relations and generalise to new unseen data.
Kopparti, R. M., Weyde, T.
core   +1 more source

Tumour–host interactions in Drosophila: mechanisms in the tumour micro‐ and macroenvironment

Molecular Oncology, EarlyView.
This review examines how tumour–host crosstalk takes place at multiple levels of biological organisation, from local cell competition and immune crosstalk to organism‐wide metabolic and physiological collapse. Here, we integrate findings from Drosophila melanogaster studies that reveal conserved mechanisms through which tumours hijack host systems to ...
José Teles‐Reis, Tor Erik Rusten
wiley   +1 more source

RaMBat: Accurate identification of medulloblastoma subtypes from diverse data sources with severe batch effects

Molecular Oncology, EarlyView.
To integrate multiple transcriptomics data with severe batch effects for identifying MB subtypes, we developed a novel and accurate computational method named RaMBat, which leveraged subtype‐specific gene expression ranking information instead of absolute gene expression levels to address batch effects of diverse data sources.
Mengtao Sun, Jieqiong Wang, Shibiao Wan
wiley   +1 more source