Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
22
datasets available to search
ShareScore release 0.9.0
Dataset results
22 results for “DNN”
Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning
<p>This repository provides the data used for the experiments of the paper "Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning" by Hazem Fahmy, Fabrizio Pastore, Mojtaba Bagherzadeh, and Lionel Briand appearing in IEEE Transactions on Reliability (doi: 10.1109/TR.2021.3074750)</p> <p>Deep neural networks (DNNs) are increasingly important in safety-critical systems, for example in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the functional safety of DNN-based components.</p> <p>We observe three major challenges with existing practices regarding DNNs in safety-critical systems: (1) scenarios that are underrepresented in the test set may lead to serious safety violation risks, but may, however, remain unnoticed; (2) char- acterizing such high-risk scenarios is critical for safety analysis; (3) retraining DNNs to address these risks is poorly supported when causes of violations are difficult to determine.</p> <p>To address these problems in the context of DNNs analyzing images, we propose HUDD, an approach that automatically supports the identification of root causes for DNN errors. HUDD identifies root causes by applying a clustering algorithm to heatmaps capturing the relevance of every DNN neuron on the DNN outcome. Also, HUDD retrains DNNs with images that are automatically selected based on their relatedness to the identified image clusters.</p> <p>We evaluated HUDD with DNNs from the automotive domain. HUDD was able to identify all the distinct root causes of DNN errors, thus supporting safety analysis. Also, our retraining approach has shown to be more effective at improving DNN accuracy than existing approaches.</p> <p> </p>
EPTGODD-WHU: Ensemble Precipitation and Temperature from CMIP6 GCMs optimized by OLS-DT-DNN methods integration (1850-2100)
<p>This monthly global climate dataset EPTGODD-WHU (precipitation and mean temperature variables with grid size of 0.5°×0.5°) was ensembled from 16 selected CMIP6 GCMs. The published dataset was optimized by OLS (Ordinary Linear Square)-DT (Decision Tree)-DNN (Deep Neural Network) methods integration. The CF (Climate and Forecast) v1.6 was employed as the guideline for NetCDF4 format. The periods of temperature files can be divided into historical (1850-1900) and future (2015-2100) periods. For precipitation, this product provides future (2015-2100) period. Three future scenarios (SSP1-2.6, SSP2-4.5 and SSP5-8.5) were selected for both variables. The units of this dataset are degrees Celsius and mm/month for temperature and precipitation, respectively. Each NetCDF4 file in this dataset includes three dimensions (time, latitude (-89.75°N to 89.75°N) and longitude (-179.75°E to 179.75°E)).</p>
Composite Embedding Systems Based on DNN-HMM and Attention End-To-End for ZeroSpeech2017 track1 (1)
<p>Deep neural networks (DNNs) were trained for posterior and bottleneck features using Japanese and other language speech data. We explore various DNN types, their combinations, and dimension reduction by principal component analysis (PCA).</p> <p>This version (version 1) extracts DNN bottleneck features obtained from GMM based SAT features. The DNN and GMM were trained by speech data from the corpus of spontaneous Japanese (CSJ).</p>
Composite Embedding Systems Based on DNN-HMM and Attention End-To-End for ZeroSpeech2017 track1 (2)
<p>Deep neural networks (DNNs) were trained for posterior and bottleneck features using Japanese and other language speech data. We explore various DNN types, their combinations, and dimension reduction by principal component analysis (PCA).</p> <p>This version (version 2 ) concatenates CSJ feature vector and PCA compressed feature vector made from attention end-to-end feature.</p> <p>X:CSJ feature (60 dim bottleneck, (version 1 feature))</p> <p>S:Attention end-to-end feature (320 dim)</p> <p>T:PCA(S) (60 dim)</p> <p>Z=concat(X,T)</p>
ANI-1 dataset with added atomic volume ratios restricted to CHNO atoms for DNN-MBD
<p>ANI-1 dataset with added atomic volume ratios restricted to CHNO atoms for DNN-MBD</p>
Soil moisture in %(m3/m3) at 4 layer at 1000 m resolution in Qinghai-Tibet Plateau (QTP_DNN_Sm_L2)
<p>Based on the deep neural network, using the SMAP and ERA5 datasets as the target data, and considering the elements of the water cycle process and environmental factors as predictor variables for training, a daily multi-layer soil moisture dataset with a resolution of 1000 meters from 2001 to 2020 was produced. The data set is stored as integer data, scale=100000.</p> <p> </p> <p>File naming convention:</p> <p>2001..2020 = time reference: period 2001-2020,</p> <p>QTP_DNN_Sm = Dataset ID,</p> <p>L1..L4 = 4 layer soil depth (0-7cm, 7-28cm, 28-100cm, 100-289cm),</p> <p>day1..day365/day366 = Date order within the year (January 1st - December 31st),</p> <p>pkl = Data storage format.</p>
Soil moisture in %(m3/m3) at 4 layer at 1000 m resolution in Qinghai-Tibet Plateau (QTP_DNN_Sm_L1)
<p>Based on the deep neural network, using the SMAP and ERA5 datasets as the target data, and considering the elements of the water cycle process and environmental factors as predictor variables for training, a daily multi-layer soil moisture dataset with a resolution of 1000 meters from 2001 to 2020 was produced. The data set is stored as integer data, scale=100000.</p> <p> </p> <p>File naming convention:</p> <p>2001..2020 = time reference: period 2001-2020,</p> <p>QTP_DNN_Sm = Dataset ID,</p> <p>L1..L4 = 4 layer soil depth (0-7cm, 7-28cm, 28-100cm, 100-289cm),</p> <p>day1..day365/day366 = Date order within the year (January 1st - December 31st),</p> <p>pkl = Data storage format.</p>
Soil moisture in %(m3/m3) at 4 layer at 1000 m resolution in Qinghai-Tibet Plateau (QTP_DNN_Sm_L3)
<p>Based on the deep neural network, using the SMAP and ERA5 datasets as the target data, and considering the elements of the water cycle process and environmental factors as predictor variables for training, a daily multi-layer soil moisture dataset with a resolution of 1000 meters from 2001 to 2020 was produced. The data set is stored as integer data, scale=100000.</p> <p> </p> <p>File naming convention:</p> <p>2001..2020 = time reference: period 2001-2020,</p> <p>QTP_DNN_Sm = Dataset ID,</p> <p>L1..L4 = 4 layer soil depth (0-7cm, 7-28cm, 28-100cm, 100-289cm),</p> <p>day1..day365/day366 = Date order within the year (January 1st - December 31st),</p> <p>pkl = Data storage format.</p>
Soil moisture in %(m3/m3) at 4 layer at 1000 m resolution in Qinghai-Tibet Plateau (QTP_DNN_Sm_L4)
<p>Based on the deep neural network, using the SMAP and ERA5 datasets as the target data, and considering the elements of the water cycle process and environmental factors as predictor variables for training, a daily multi-layer soil moisture dataset with a resolution of 1000 meters from 2001 to 2020 was produced. The data set is stored as integer data, scale=100000. </p> <p> </p> <p>File naming convention:</p> <p>2001..2020 = time reference: period 2001-2020,</p> <p>QTP_DNN_Sm = Dataset ID,</p> <p>L1..L4 = 4 layer soil depth (0-7cm, 7-28cm, 28-100cm, 100-289cm),</p> <p>day1..day365/day366 = Date order within the year (January 1st - December 31st),</p> <p>pkl = Data storage format.</p>
Unsupervised Acoustic Modeling using Autoencoder-DNN with HMM Posteriograms (system #3)
<p>DNN trained with Autoencoder features with HMM posteriograms.</p>
Pre-trained DNN model data for pruning example code
<p>Pre-trained DNN model datasets for example codes of neural network pruning.</p> <p>Example pruning codes are published in "https://github.com/FujitsuLaboratories/CAC/tree/main/cac/pruning".</p>
MARTENS framework: examples of DNN mispredictions discovered for the two use cases
<p>The folder contains examples of the mispredicitons of the DNN models discoverd for the two use cases studied as a part of development of MARTENS framework at Sycodal.</p>
Supplementary Materials of "Understanding flow characteristics from tsunami deposits at Odaka, Joban coast, using a DNN inverse model" by Mitra, Naruse and Abe
<p>This is a supplementary figures for the manuscript entitled "Understanding flow characteristics from tsunami deposits at Odaka, Joban coast, using a DNN inverse model" submitted to NHESS.</p>
Prediction of Postoperative Outcomes After TKA Using Instrumented Insoles and DNN
ClinicalTrials.gov study NCT07367789. IPD Sharing: NO. Countries: 1. Publications: 21.
Experiment-based DNN approach for power allocation with a metasurface
Open the record for dataset details and reuse information.
Pruned DNN model data for pruning example code
<p>Pruned DNN model datasets for example codes of neural network pruning.</p> <p>Example pruning codes are published in "https://github.com/FujitsuLaboratories/CAC/tree/main/cac/pruning".</p>
PBE, PBE0, B86bPBE data and relative DNN-MBDQ dispersion corrections for S66x8 and S22 data sets.
<p>PBE, PB0 and B86bPBE interaction energy data for the S66x8 and/or S22<br> data sets as well as their relative DNN-MBDQ dispersion corrections for the different range-separation parameters (β) discussed.</p>
(Artifact) Understanding Model Weaknesses: A Path to Strengthening DNN-Based Android Malware Detection
Open the record for dataset details and reuse information.
Identification of Replication Timing Domains Using DNN-HMM
GEO Series GSE53984. Homo sapiens. 0 samples. Type: Third-party reanalysis; Other.
DNN-CALIPO-PRODUCTS
<p>CALIPO bbp products by DNN methods</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.