Results 1 to 10 of about 98,687 (237)
Modeling Interval Timing by Recurrent Neural Nets [PDF]
Frontiers in Integrative Neuroscience, 2019 The purpose of this study was to take a new approach in showing how the central nervous system might encode time at the supra-second level using recurrent neural nets (RNNs).
T. Raphan, Eugene Dorokhin, A. Delamater
semanticscholar +5 more sources
Automatic Synthesis of Neurons for Recurrent Neural Nets [PDF]
arXiv.org, 2022 We present a new class of neurons, ARNs, which give a cross entropy on test data that is up to three times lower than the one achieved by carefully optimized LSTM neurons.
R. Olsson, C. Tran, L. Magnusson
semanticscholar +3 more sources
Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets [PDF]
arXiv.org, 2022 The statistical supervised learning framework assumes an input-output set with a joint probability distribution that is reliably represented by the training dataset.
Deborah Pereg +3 more
semanticscholar +3 more sources
Multicategory choice modeling by recurrent neural nets
Journal of Retailing and Consumer ServicesWe investigate three variants of recurrent neural nets capable to reproduce dynamic effects in a flexible way. We compare these recurrent nets to non-recurrent multilayer perceptrons (MLPs) and to multivariate logit models.
H. Hruschka
semanticscholar +3 more sources
Unsupervised Feature Learning Using Recurrent Neural Nets for Segmenting Hyperspectral Images
IEEE Geoscience and Remote Sensing Letters, 2020 Although deep learning is gaining more widespread use in hyperspectral image analysis, it is challenging to train high-capacity models in a supervised way—ground-truth sets are expensive to obtain, and they are practically always extremely imbalanced. To
Lukasz Tulczyjew, M. Kawulok, J. Nalepa
semanticscholar +2 more sources
Overcoming the Vanishing Gradient Problem during Learning Recurrent Neural Nets (RNN)
Asian Journal of Applied Science and Engineering, 2020 Artificial neural nets have been equipped with working out the difficulty that arises as a result of exploding and vanishing gradients. The difficulty of working out is worsened exponentially particularly in deep learning understanding.
Takudzwa Fadziso
semanticscholar +2 more sources
NowCasting-Nets: Representation Learning to Mitigate Latency Gap of Satellite Precipitation Products Using Convolutional and Recurrent Neural Networks [PDF]
IEEE Transactions on Geoscience and Remote Sensing, 2021 Accurate and timely estimation of precipitation is critical for issuing hazard warnings (e.g., for flash floods or landslides). Current remotely sensed precipitation products have a few hours of latency, associated with the acquisition and processing of ...
M. Ehsani +4 more
semanticscholar +1 more source
Bayesian error propagation for neural-net based parameter inference
The Open Journal of Astrophysics, 2022 Neural nets have become popular to accelerate parameter inferences, especially for the upcoming generation of galaxy surveys in cosmology. As neural nets are approximative by nature, a recurrent question has been how to propagate the neural net's ...
Daniela Grandón, Elena Sellentin
doaj +1 more source
Sensors, 2021 Sea fog is a natural phenomenon that reduces the visibility of manned vehicles and vessels that rely on the visual interpretation of traffic. Fog clearance, also known as fog dissipation, is a relatively under-researched area when compared with fog ...
Jin Hyun Han +5 more
doaj +1 more source
Mack-Net model: Blending Mack’s model with Recurrent Neural Networks
Expert Systems with Applications, 2022 In general insurance companies, a correct estimation of liabilities plays a key role due to its impact on management and investing decisions. Since the Financial Crisis of 2007-2008 and the strengthening of regulation, the focus is not only on the total reserve but also on its variability, which is an indicator of the risk assumed by the company. Thus,
Eduardo Ramos-Pérez +2 more
openaire +3 more sources