Find research datasets worth reusing

opencc-by-4.0Nov 2022View details →

Semi-Recurrent Neural Networks In IllustrisTNG And N-Body Simulations

This is the official data repository for the MNRAS publication <a href="https://arxiv.org/abs/2203.12702">Modelling the galaxy-halo connection using semi-recurrent neural networks</a>, and subsequent works <a href="https://arxiv.org/abs/2409.16548">Optimised neural network predictions of galaxy formation histories using semi-stochastic corrections</a> and <a href="https://arxiv.org/abs/2409.16079">Evaluating the galaxy formation histories predicted by a neural network in pure dark matter simulations</a>. For details on access and utilisation of the data and code, see documentation.pdf in the affiliated <a href="https://github.com/hgc4/TNG-Networks">GitHub repository</a>.

dryad40/100

Data for: Brain control of bimanual movement enabled by recurrent neural networks

Brain-computer interfaces have so far focused largely on enabling the control of a single effector, for example a single computer cursor or robotic arm. Restoring multi-effector motion could unlock greater functionality for people with paralysis (e.g., bimanual movement). However, it may prove challenging to decode the simultaneous motion of multiple effectors, as we recently found that a compositional neural code links movements across all limbs and that neural tuning changes nonlinearly during dual-effector motion. In this study, we demonstrate the feasibility of high-quality bimanual control of two cursors via neural network (NN) decoders. This dataset represents all neural activity recorded during these experiments. This includes the neural activity corresponding to unimanual and bimanual hand movements during (1) instructed delay experiments and (2) real-time BCI control of two cursors. Code associated with the data can be found here: <a href="https://github.com/d-r-deo/bimanualBCI" target="_blank" rel="noopener">https://github.com/d-r-deo/bimanualBCI</a>

opencc-zeroDec 2023View details →

opencc-by-4.0Nov 2021View details →

Data of "Recurrent Neural Networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step."

Data related to =========== title = "Recurrent Neural Networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step.", journal = "Computer Methods in Applied Mechanics and Engineering", volume ="390", year = "2022", doi = "https://doi.org/<a href="http://dx.doi.org/10.1016/j.cma.2021.114476">10.1016/j.cma.2021.114476</a> ", pages = "114476 ", author = "Wu, Ling and Noels, Ludovic" We would be grateful if you could cite the paper in the case in which you are using the data   The files replace version 1 whose zip was corrupted.

opencc-by-4.0Nov 2021View details →

Classification of blood cells dynamics with convolutional and recurrent neural networks: a sickle cell disease case study

The fraction of red blood cells (RBC) adopting a specific motion under low shear flow is a promising inexpensive marker for monitoring the clinical status of patients with sickle cell disease (SCD). Its high-throughput measurement relies on the video analysis of thousands of cell motions for each blood sample to eliminate a large majority of unreliable samples(out of focus or overlapping cells) and discriminate between tank-treading and flipping motion, characterizing highly and poorly deformable cells respectively. These videos are of different durations (from 6 to more than 100 frames). This dataset contains four adult patients with SCD. They were enrolled in the study Drepaforme (approved by the institutional review board CPP Ouest 6 under the reference n°2018A00679-46) and were sampled weekly for several months. The movies were processed using in-house routines in Matlab (Matlab, R2016a) and RBC were detected individually and tracked over time. The database provided in this repository are already pre-processed sequences of tracked and centered RBC over time, each time step image being normalized to 31x31 pixels. Within the 32 experiments, the total number of sequences (or samples) is nearly 150 000. All sequences were semi-automatically labelled into 3 classes, depending on the dynamic of the cell: tank-treading, flipping and unreliable (140 000 are unreliable). The percentage of tank-treading cells with respect to all reliable cells (tank-treading+flipping)  in every experiment is the final goal of this study. This dataset is very interesting to the community as it is a large database for cell dynamics classification: the class depends on the movement of the cell. An automatic processing of the database using a 2-stage deep learning model is available here https://github.com/icannos/redbloodcells_disease_classification For opening the data in python:   from scipy.io import loadmat   x=loadmat('BG20191003shear10s01_Export.mat')   * x['Norm_Tab'] is of size nb_samples x max_len_sequences x 31 x 31, where max_len_sequences is the length of the longest sequence of the series, typically ~150 to 180. The other sequences are padded with 31x31 zero matrices at the end in order to fill this maximal length.   * x['Labels_Num'] is the corresponding label of each sequence, of size nb_samples. Label can be:         - 0 : "tank-treading" (or healthy)         - 1 : "flipping" (or tumbling, i.e. related to a SCD)         - 2 : "unreliable"

opencc-by-4.0Nov 2020View details →

Polymeric Property Prediction Using Recurrent Neural Networks with Optimizations

Database of the Dielectric Polymers used for training and testing of the developed Recurrent Neural Network models (DOI:10.5281/zenodo.4280446)

opencc-by-4.0Jun 2024View details →

Self Consistent Recurrent Neural Network for Path Dependent Deformation

Data and Machine Learning codes for the paper: <ul> <li>Title : Self Consistent Recurrent Neural Network for Path Dependent Deformation</li> </ul> Abstract : Current neural network (NN) structures can learn patterns from data points with historical dependence. Specifically, in natural language processing (NLP), sequential learning has transitioned from recurrence-based architectures to transformer-based architectures. However, it is not known in advance which NN architectures will perform best on datasets containing deformation history due to mechanical loading. Thus, this study ascertains the appropriateness of 1D-convolutional, recurrent, and transformer-based architectures for predicting material failure based on the earlier states in the form of deformation history. Following this investigation, the crucial issues arising from the mathematical computation process of the best-performing NN architectures and the physical properties of the deformation paths are examined in detail. Additionally, we propose a novel and adaptable RNN approach to address the fundamental challenges of truncation and consistency related to obtaining estimations that are compatible with the natural physical properties of deformation paths. This study will serve as a foundation for localization estimation and pave the way for future endeavors to propose further solutions to encountered challenges.

opencc-by-4.0Nov 2018View details →

Revealing Ferroelectric Switching Character Using Deep Recurrent Neural Networks

The ability to manipulate domains and domain walls underpins function in a range of next-generation applications of ferroelectrics. While there have been demonstrations of controlled nanoscale manipulation of domain structures to drive emergent properties, such approaches lack an internal feedback loop required for automation. Here, using a deep sequence-to-sequence autoencoder we automate the extraction of features of nanoscale ferroelectric switching from multichannel hyperspectral band-excitation piezoresponse force microscopy of tensile-strained PbZr0.2Ti0.8O3 with a hierarchical domain structure. Using this approach, we identify characteristic behavior in the piezoresponse and cantilever resonance hysteresis loops, which allows for the classification and quantification of nanoscale-switching mechanisms. Specifically, we are able to identify elastic hardening events which are associated with the nucleation and growth of charged domain walls. This work demonstrates the efficacy of unsupervised neural networks in learning features of the physical response of a material from nanoscale multichannel hyperspectral imagery and provides new capabilities in leveraging multimodal in operando spectroscopies and automated control for the manipulation of nanoscale structures in materials.

dryad40/100

Data for: Brain control of bimanual movement enabled by recurrent neural networks

Open the record for dataset details and reuse information.

publicJan 2024View details →

opencc-by-4.0Nov 2024View details →

Code and partial data used in "Vertically recurrent neural networks for sub-grid parameterization"

This repository contains the RNN training and evaluation code used in the paper Vertically recurrent neural networks for sub-grid parameterization   <ul> <li> The radiative transfer emulation data can be accessed with through a Climetlab plugin (<a href="https://pypi.org/project/climetlab-maelstrom-radiation/">Climetlab-maelstrom-radiation</a>).  Datasets are downloaded and explained in the demo notebook here <a href="https://git.ecmwf.int/projects/MLFET/repos/maelstrom-radiation/browse/notebooks/demo_radiation.ipynb" rel="nofollow">https://git.ecmwf.int/projects/MLFET/repos/maelstrom-radiation/browse/notebooks/demo_radiation.ipynb</a> In addition the full training and testing code used in the paper is uploaded here (pu-maelstrom-radiation.tar.gz).</li> <li> </li> </ul> Three parameterization problems from earlier studies are also included (we have modified the code from these papers to incorporate RNNs):  <ul> <li>non-orographic gravity wave drag (<a href="https://doi.org/10.1029/2021MS002477">Chantry et al. 2021</a>)  <ul> <li>Based on TensorFlow</li> <li>This repository uses the CliMetLab plugin and downloads the data from the European Weather Cloud</li> </ul> </li> <li>non-local parameterization (<a href="https://doi.org/10.1029/2022MS002984">Wang et al. 2022</a>) <ul> <li>The new code is based on TensorFlow, so you'll need both PyTorch and TensorFlow to run everything</li> <li>See original paper for data access</li> </ul> </li> <li>moist physics (Han et al. <a href="https://doi.org/10.1029/2022MS003508">2023</a>, <a href="https://doi.org/10.1029/2020MS002076">2020</a>)  <ul> <li>Based on TensorFlow and PyTorch. This one has the most additions, e.g. code to generate a TensorFlow TFRecord dataset from the raw netCDF data archived in the original paper, autoregressive training and experimental model architectures in PyTorch</li> <li>See original paper for data access</li> </ul> </li> </ul> Each of the code repos (unpack the tars) have an updated README. References: <table> <tbody> <tr> <td> <div>Chantry, M., Hatfield, S., Dueben, P., Polichtchouk, I., & Palmer, T. (2021). Machine learning emulation of gravity wave drag in numerical weather forecasting. Journal of Advances in Modeling Earth Systems, 13(7), e2021MS002477</div> <div> </div> <div> <div>Han, Y., Zhang, G. J., Huang, X., & Wang, Y. (2020). A moist physics parameterization based on deep learning. Journal of Advances in Modeling Earth Systems, 12(9), e2020MS002076.</div> </div> <div> </div> <div>Han, Y., Zhang, G. J., & Wang, Y. (2023). An ensemble of neural networks for moist physics processes, its generalizability and stable integration. Journal of Advances in Modeling Earth Systems, 15(10), e2022MS003508</div> <div> </div> <div>Wang, P., Yuval, J., & O’Gorman, P. A. (2022). Non‐local parameterization of atmospheric subgrid processes with neural networks. Journal of Advances in Modeling Earth Systems, 14(10), e2022MS002984.</div> </td> </tr> <tr></tr> </tbody> </table> <div> </div>

opencc-by-4.0Dec 2020View details →

Long short-term memory (LSTM) recurrent neural network for muscle activity detection

Background: The accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.   Methods: First, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager–Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis. Results: The proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR. Conclusions: The presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/ distinction of muscle activity from background noise in sEMG signals.

opencc-by-4.0May 2022View details →

Data for "Predicting aggregate morphology of sequence-defined macromolecules with Recurrent Neural Networks"

These are the data associated with the paper, "Predicting aggregate morphology of sequence-defined macromolecules with Recurrent Neural Networks" (DOI 10.1039/D2SM00452F). Three of the directories contains subdirectories with `GSD` files dumped from HOOMD. The other contains pretrained RNN models as TorchScript binaries exported from PyTorch.

opencc-by-sa-4.0Jun 2018View details →

Medical Concept Normalization in Social Media Posts with Recurrent Neural Networks

Text mining of scientific libraries and social media has already proven itself as a reliable tool for drug repurposing and hypothesis generation. The task of mapping a disease mention to a concept in a controlled vocabulary, typically to the standard thesaurus in the Unified Medical Language System (UMLS), is known as medical concept normalization. This task is challenging due to the differences in medical terminology between health care professionals and social media texts coming from the lay public. To bridge this gap, we use sequence learning with recurrent neural networks and semantic representation of one- or multi-word expressions: we develop end-to-end architectures directly tailored to the task, including bidirectional Long Short-Term Memory and Gated Recurrent Units with an attention mechanism and additional semantic similarity features based on UMLS. Our evaluation over a standard benchmark shows that recurrent neural networks improve results over an effective baseline for classification based on convolutional neural networks. A qualitative examination of mentions discovered in a dataset of user reviews collected from popular online health information platforms as well as quantitative evaluation both show improvements in the semantic representation of health-related expressions in social media.

dryad36/100

Myoelectric prosthesis control using recurrent convolutional neural network regression mitigates the limb position effect

Open the record for dataset details and reuse information.

publicJun 2025View details →

opencc-by-4.0Jun 2020View details →

Data of A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths

<pre>Data related to the publication (we would be grateful if you could cite the paper in the case in which you are using the data) title = "A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths", journal = "Computer Methods in Applied Mechanics and Engineering", pages = " 113234", year = "2020", issn = "0045-7825", doi = "https://doi.org/10.1016/j.cma.2020.113234", author = "Wu, Ling and Nguyen, Van Dung and Kilingar, Nanda Gopala and Noels, Ludovic"</pre>

opencc-by-4.0Apr 2020View details →

Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment

This repository contains the raw results (by word information-theoretic measures for the experimental stimuli) and the LSTM models analyzed in <a href="https://www.aclweb.org/anthology/2020.acl-main.179/">Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment</a>. The models from the synthetic experiments are given in the synthetic archive, as well as the training data generation script. There is a README included that gives more details for recreating/evaluating results from those experiments. The naming convention for each model in the models directory is: [Language]_hidden[Hidden Units]_batch[Batch Size]_dropout[Dropout Rate]_lr[Learning Rate]_[Model Number].pt Language: en for English and es for Spanish Hidden Units: All models had two layers with 650 hidden units per layer Batch Size: The size of the batch (128 for English, 64 for Spanish) Dropout Rate: All models used a dropout rate of 0.2 Learning Rate: All models has a learning rate of 20 Model Number: Identifier of the model (English model 0 is the best model from <a href="https://github.com/facebookresearch/colorlessgreenRNNs">Gulordava et al. (2018)</a>)

dryad32/100

Double attention recurrent convolution neural network for answer selection

Answer selection is one of the key steps in many Question Answering (QA) applications. In this paper, a new deep model with two kinds of attention is proposed for answer selection: the Double Attention Recurrent Convolution Neural Network (DARCNN). Double attention means self-attention and cross-attention. The design inspiration of this model came from the Transformer in the domain of machine translation. Self-attention can directly calculate dependencies between words regardless of the distance. However, self-attention ignores the distinction between its surrounding words and other words. Thus, we design a decay self-attention that prioritizes local words in a sentence. In addition, cross-attention is established to achieve interaction between question and candidate answer. With the outputs of self-attention and decay self-attention, we can get two kinds of interactive information via cross-attention. Finally, using the feature vectors of the question and answer, elementwise multiplication is used to combine with them and multi-layer perceptron (MLP) is used to predict the matching score. Experimental results on four QA datasets containing Chinese and English show that DARCNN performs better than other answer selection models, thereby demonstrating the effectiveness of self-attention, decay self-attention and cross-attention in answer-selection tasks.

opencc-zeroApr 2020View details →

opencc-by-4.0Mar 2024View details →

Learning Useful Representations of Recurrent Neural Network Weight Matrices

Dataset of RNN weights for the ICML 2024 paper "Learning Useful Representations of Recurrent Neural Network Weight Matrices".  See <a title="GitHub repository" href="https://github.com/vincentherrmann/rnn-weights-representation-learning">https://github.com/vincentherrmann/rnn-weights-representation-learning</a>. <h1> </h1>

opencc-by-4.0Jan 2019View details →

Data for "Efficient neural decoding of self-location with a deep recurrent network"

Data for reproducing results with Bayesian decoders (MLE and Bayesian with memory) reported in the article "Efficient neural decoding of self-location with a deep recurrent network".   This data should be used with the code found in https://github.com/NeuroCSUT/RatGPS and should be placed in the Bayesian/Data folder of the codebase.