Results 81 to 90 of about 296,489 (278)
Learning text representation using recurrent convolutional neural network with highway layers [PDF]
, 2016 Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with highway layers ...
Luo, Rui +3 more
core +1 more source
Memristive recurrent neural network
Neurocomputing, 2018 Abstract It is reported a continuous-time neural network in CMOS that uses memristors. These nanodevices are used to achieve some analog functions such as constant current sourcing, decaying term emulation, and resistive connection; all of them representing parameters of the neural network.
Gerardo Marcos Tornez-Xavier +3 more
openaire +1 more source
Temporal-Kernel Recurrent Neural Networks [PDF]
Neural Networks, 2010 A Recurrent Neural Network (RNN) is a powerful connectionist model that can be applied to many challenging sequential problems, including problems that naturally arise in language and speech. However, RNNs are extremely hard to train on problems that have long-term dependencies, where it is necessary to remember events for many timesteps before using ...
Ilya Sutskever, Geoffrey E. Hinton
openaire +2 more sources
Molecular Oncology, EarlyView.Keratin 19 (KRT19) is overexpressed in high‐grade serous ovarian cancer with high levels of Kallikrein‐related peptidases (KLK) 4–7 and is associated with poor survival. In vivo analyses demonstrate that elevated KRT19 increases peritoneal tumour burden.
Sophia Bielesch +13 more
wiley +1 more source
Reversible Recurrent Neural Networks
CoRR, 2018 Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory requirements of training, as hidden ...
Matthew MacKay +3 more
openaire +3 more sources
Batch normalized recurrent neural networks [PDF]
2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016 Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that normalizing intermediate representations of neural networks can significantly improve convergence rates in ...
César Laurent +4 more
openaire +2 more sources
Somatic mutational landscape in von Hippel–Lindau familial hemangioblastoma
Molecular Oncology, EarlyView.The causes of central nervous system (CNS) hemangioblastoma in Von Hippel–Lindau (vHL) disease are unclear. We used Whole Exome Sequencing (WES) on familial hemangioblastoma to investigate events that underlie tumor development. Our findings suggest that VHL loss creates a permissive environment for tumor formation, while additional alterations ...
Maja Dembic +5 more
wiley +1 more source
The Power of Linear Recurrent Neural Networks
, 2020 Recurrent neural networks are a powerful means to cope with time series. We show how a type of linearly activated recurrent neural networks, which we call predictive neural networks, can approximate any time-dependent function f(t) given by a number of ...
Litz, Sandra +3 more
core
Adverse Drug Reaction Classification With Deep Neural Networks [PDF]
, 2016 We study the problem of detecting sentences describing adverse drug reactions (ADRs) and frame the problem as binary classification. We investigate different neural network (NN) architectures for ADR classification.
He, Yulan +3 more
core +1 more source
Temporal overdrive recurrent neural network [PDF]
2017 International Joint Conference on Neural Networks (IJCNN), 2017 In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics. The proposed network is composed by several recurrent groups of neurons that are trained to separately adapt to each timescale, in order to improve the system identification process.
Filippo Maria Bianchi +3 more
openaire +3 more sources