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.
921
datasets available to search
ShareScore release 0.7.1
Dataset results
921 results for “neural networks”
Transcriptome analysis of Drosophila neural stem cells reveals a transcriptional network for self-renewal.
GEO Series GSE38764. Drosophila melanogaster. 8 samples. Type: Expression profiling by high throughput sequencing.
Dissecting neural differentiation regulatory networks through epigenetic footprinting
GEO Series GSE62193. Homo sapiens. 99 samples. Type: Expression profiling by high throughput sequencing; Genome binding/occupancy profiling by high throughput sequencing; Methylation profiling by high throughput sequencing; Other.
A functional genomics atlas enhanced by convolutional neural networks facilitates clinical interpretation of disease relevant variants in non-coding regulatory elements [wt RNA-seq]
GEO Series GSE267549. Homo sapiens. 2 samples. Type: Expression profiling by high throughput sequencing.
Reconstruction of the global neural crest gene regulatory network in vivo [bulk RNA-seq]
GEO Series GSE121526. Gallus gallus. 11 samples. Type: Expression profiling by high throughput sequencing.
Erythropoietin Signaling Regulates Key Epigenetic and Transcription Networks in Fetal Neural Progenitor Cells
GEO Series GSE99372. Mus musculus. 5 samples. Type: Expression profiling by high throughput sequencing.
Identification of a selective G1-phase benzimidazolone inhibitor by a senescence-targeted virtual screen using artificial neural networks
GEO Series GSE72621. Homo sapiens. 38 samples. Type: Expression profiling by array.
A functional genomics atlas enhanced by convolutional neural networks facilitates clinical interpretation of disease relevant variants in non-coding regulatory elements [STARR-RNA-seq]
GEO Series GSE263335. Homo sapiens. 16 samples. Type: Expression profiling by high throughput sequencing.
Identification of transcriptional targets of a network of Drosophila core promoter factors in neural stem cells
GEO Series GSE120430. Drosophila melanogaster. 12 samples. Type: Expression profiling by high throughput sequencing.
A Clock-Driven Neural Network Critical for Arousal
GEO Series GSE146166. Mus musculus. 3 samples. Type: Expression profiling by high throughput sequencing.
PTEN mutations impair CSF dynamics and cortical networks by dysregulating periventricular neural progenitors
GEO Series GSE280368. Mus musculus. 14 samples. Type: Expression profiling by high throughput sequencing.
Human neural networks with sparse TDP-43 pathology reveal NPTX2 misregulation in ALS/FTLD
GEO Series GSE230647. Homo sapiens. 28 samples. Type: Expression profiling by high throughput sequencing.
A protein interaction network of mental disorder factors in neural stem cells
GEO Series GSE70872. Mus musculus. 17 samples. Type: Genome binding/occupancy profiling by high throughput sequencing; Expression profiling by high throughput sequencing.
REST and Neural Gene Network Dysregulation in iPS Cell Models of Alzheimer’s Disease (RNA-seq data set)
GEO Series GSE117588. Homo sapiens. 6 samples. Type: Expression profiling by high throughput sequencing.
Engineered Living Systems with Self-Organizing Neural Networks: From Anatomy to Behavior and Gene Expression
GEO Series GSE295614. Xenopus laevis. 12 samples. Type: Expression profiling by high throughput sequencing.
A brain-inspired architecture for cost-efficient object recognition in shallow neural networks
<p>Demo codes for "A brain-inspired architecture for cost-efficient object recognition in shallow neural networks"</p> <p><strong>1. System requirements</strong><br> - MATLAB (2019a or 2019b is recommended.)</p> <p>- Installation of Deep Learning Toolbox</p> <p>- Uploaded codes were tested using MATLAB 2019a and 2019b.</p> <p>- No non-standard hardware is required to run the codes.</p> <p><br> <strong>2. Installation guide</strong><br> - Download "LRC_code.zip" and unzip the file.</p> <p>- Download "DATASET_ori.zip","pretrainedNet.zip" and unzip on same file.</p> <p>- Choose the proper subfolder of 'fun_modifed_toolbox' which is matched to your MATLAB version and<br> Move each file to the proper directory<br> (see the comment in line 4 of each file for proper directory e.g. 'dir = C:\Program Files\MATLAB\...')<br> </p> <p><strong>3. Instructions for use</strong><br> - By running "Main.m" and selecting code option and figure option (see line 35 - 41 on the Main.m)<br> code options :<br> i) flg_ShowRes : Show the result figure of demo code using the pretrained network (in pretrainedNet.zip)<br> ii) flg_Demo : Run the demo code using a randomly initialized network<br> figure options : flg1 - Result 1 / flg2 - Result 2 / flg3 - Result 3 </p> <p> </p> <p><strong>cf. Modified MNIST datasets</strong></p> <p>To separately examine the contribution of high and low-frequency information contained in sample images, we designed three types of modified MNIST datasets. Details are as follows:</p> <p><strong>Type 1</strong><em>: shape</em>. The “<em>shape</em>” dataset was designed by arranging a hand-written digit of 8 x 8 pixels in the center of a 28 x 28 pixels image. The dataset consists of eight categories depending on the number in the center (1 to 8). For this dataset, only local information (shape) of the digits is required for classification.</p> <p><br> <strong>Type 2</strong>: <em>position</em>. The “<em>position</em>” dataset was made by the following procedure. First, two digits of 8 x 8 pixels were randomly chosen. Second, these two digits were allocated in a 28 x 28 image, with one of the following position alignments: horizontal (top, middle, bottom), vertical (left, middle, right), or diagonal (45°, 135°). This dataset also consists of eight categories depending on the position only where the digits are located. Note that the shape of each number is irrelevant for classification.</p> <p><br> <strong>Type 3</strong>: <em>shape-position</em>. The “<em>shape-position</em>” dataset was made by the following procedure. First, a 28 x 28 pixel area was divided into four 14 x 14 areas. Second, two diagonally aligned areas were selected (either 45° or 135°). Third, one of two digits, either “7” or “9”, composed of 8 x 8 pixels was inserted into each selected area. This dataset consists of eight categories depending on both the shape and position of the digits. The reason we chose “7” and “9” among ten numbers is to adjust the difficulty of the task to be similar to that of the previous tasks. Note that this dataset requires both local information (shape) and global information (position) of the digits for classification. </p>
Data to Replicate paper Improving Bug Detection via Context-based Code Representation Learning and Attention-based Neural Networks part 2
<p>Data to Replicate paper "Improving Bug Detection via Context-based Code Representation Learning and Attention-based Neural Networks" part 2.</p> <p>The author of the paper uploaded dataset to Google Drive. These are the same files, uploaded to Zenodo. Since detection_data.tar.gz exceeded zenodo limits, I split the data into 2 parts <em>detection_data.tar.gz</em> and <em>detection_data.tar.gz</em>. This is the first part. Splitting was achieved on OS X with:</p> <pre><code>split -b 31000m "detection_data.tar.gz" "detection_data.tar.gz."</code></pre> <p>To get original file back, run</p> <pre><code>cat detection_data.tar.gz.* > detection_data.tar.gz</code></pre> <p>GitHub link to the project: <a href="https://github.com/OOPSLA-2019-BugDetection/OOPSLA-2019-BugDetection">https://github.com/OOPSLA-2019-BugDetection/OOPSLA-2019-BugDetection</a></p>
Data to Replicate paper Improving Bug Detection via Context-based Code Representation Learning and Attention-based Neural Networks part 1
<p>Data to Replicate paper "Improving Bug Detection via Context-based Code Representation Learning and Attention-based Neural Networks" part 1. Part 2 accessible here: <a href="https://doi.org/10.5281/zenodo.3719225">https://doi.org/10.5281/zenodo.3719225</a></p> <p>The author of the paper uploaded dataset to Google Drive. These are the same files, uploaded to Zenodo. Since detection_data.tar.gz exceeded zenodo limits, I split the data into 2 parts <em>detection_data.tar.gz</em> and <em>detection_data.tar.gz</em>. This is the first part. Splitting was achieved on OS X with:</p> <pre><code>split -b 31000m "detection_data.tar.gz" "detection_data.tar.gz."</code></pre> <p>To get original file back, run</p> <pre><code>cat detection_data.tar.gz.* > detection_data.tar.gz</code></pre> <p>GitHub link to the project: <a href="https://github.com/OOPSLA-2019-BugDetection/OOPSLA-2019-BugDetection">https://github.com/OOPSLA-2019-BugDetection/OOPSLA-2019-BugDetection</a></p>
Tagged formatted datasets for 'Genetically Optimized Massively Parallel Binary Neural Networks for Intrusion Detection Systems'
<p>Tagged formatted datasets used in 'Genetically Optimized Massively Parallel Binary Neural Networks for Intrusion Detection Systems' T.Murovič, A.Trost.</p>
Global ocean dimethyl sulfide climatology estimated from observations and an artificial neural network
<p>Surface ocean DMS concentrations and sea-to-air flux estimated using an Artificial Neural Network model. </p> <p><a href="https://zenodo.org/api/files/3da6a1cf-5a4c-4186-984e-20a3298facfc/DMS_Concentration_monthly_mean.csv?versionId=4dabc517-22c9-4829-84e3-5df97ef8aa74">DMS_Concentration_monthly_mean.csv</a> and <a href="https://zenodo.org/api/files/3da6a1cf-5a4c-4186-984e-20a3298facfc/DMS_Flux_Wang2020.mat?versionId=a5e8de9f-5962-4940-974b-e14731a0c466">DMS_Flux_Wang2020.mat</a> are previous versions based on BGD paper.</p> <p><a href="https://zenodo.org/api/files/3da6a1cf-5a4c-4186-984e-20a3298facfc/DMS_clim_Wang20_v1.mat?versionId=02ca48ed-306e-44da-a406-3ac48f75e811">DMS_clim_Wang20_v1</a>.mat and <a href="https://zenodo.org/api/files/3da6a1cf-5a4c-4186-984e-20a3298facfc/Sea2Air_Flux_Wang20_v1.mat?versionId=6244f1bc-26d1-4f5e-b6ea-93be132bf6d3">Sea2Air_Flux_Wang20_v1.mat</a> are newer versions based on BGD paper revision.</p> <p>PMEL_NAAMES_* data are raw DMS data along with environmental parameters, so interested user can play with the models.</p> <p>The ANN models can be found in the the following repository: <a href="https://github.com/weileiw/ANN-DMS-code">https://github.com/weileiw/ANN-DMS-code</a></p> <p> </p> <p> </p> <p> </p>
Benchmark datasets used in "Classification of Periodic Variables with Cyclic-Permutation Invariant Neural Networks"
<p>To aid the reproducibility of the results in the paper “Classification of Periodic Variables with Cyclic-Permutation Invariant Neural Networks,” we make our aggregation of the following data available. Code used to load the data and generate the results can be found at <a href="https://github.com/kmzzhang/periodicnetwork">https://github.com/kmzzhang/periodicnetwork</a>. These datasets have been constructed from publicly available data sources. If you use these datasets, please cite the original papers [1, 2, 3], in addition to ours [TBD]. Others might find this data useful for testing time-series inference techniques.</p> <p>[1] Jayasinghe, T. et al. The ASAS-SN catalogue of variable stars I: The Serendipitous Survey. Monthly Notices of the Royal Astronomical Society 477, 3145–3163 (2018). URL <a href="https://academic.oup.com/mnras/article/477/3/3145/4961151">https://academic.oup.com/mnras/article/477/3/3145/4961151</a>.<br> [2] Alcock, C. et al. The MACHO Project LMC Variable Star Inventory.II.LMC RR Lyrae Stars- Pulsational Characteristics and Indications of a Global Youth of the LMC. The Astronomical Journal 111, 1146 (1996). URL <a href="http://adsabs.harvard.edu/abs/">http://adsabs.harvard.edu/abs/</a>1996AJ....111.1146A.<br> [3] Udalski, A. The Optical Gravitational Lensing Experiment. Real Time Data Analysis Systems in the OGLE-III Survey. Acta Astronomica 53, 291–305 (2003). URL http: <a href="https://bloomlab-berkeley.slack.com//adsabs.harvard.edu/abs/2003AcA....53..291U">//adsabs.harvard.edu/abs/2003AcA....53..291U</a>.</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.