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.
3
datasets available to search
ShareScore release 0.9.0
Dataset results
3 results for “zero-shot learning”
Physical-Layer Fingerprinting of LoRa devices using Supervised and Zero-Shot Learning
<p>This dataset contains all raw signals (complex float I/Q samples) used in the LoRa fingerprinting experiments of the paper entitled "Physical-Layer Fingerprinting of LoRa devices using Supervised and Zero-Shot Learning". There are 4 databases included: lora1msps, lora2msps, lora5msps, and lora10msps. Each document in the databases is a symbol extracted from a 4-byte random payload LoRa frame, transmitted by a RN2483 radio and received by a USRP B210 sampling at a rate corresponding to the database name. A total of 22 different transmitters were used. For more information, please consult the paper. The document structure is as follows:</p> <ul> <li>_id: Unique MongoDB document ID</li> <li>chirp: Base 64 encoded binary float complex I/Q data</li> <li>field: Symbol location inside a LoRa frame</li> <li>tag: Name of the device that sent the frame</li> <li>date: Time and date of reception</li> <li>fn: Frame number</li> <li>rand: Random number for sorting</li> </ul> <p><strong>How to import</strong></p> <p>Extract the tar archive. Inside the directory, run the following command to import the lora2msps database:</p> <p><em>mongorestore --gzip -d lora2msps ./lora2msps</em></p> <p>This process can be repeated for each dataset. Alternatively, all datasets can be imported automatically by executing:</p> <p><em>mongorestore --gzip . </em></p> <p><strong>How to use</strong></p> <p>After the data has been imported, an experiment can be run by simply providing the corresponding config file to tf_train (see https://github.com/rpp0/lora-phy-fingerprinting), e.g.:</p> <p><em>./tf_train.py train conf/experiment_lora2msps_mlp.conf</em></p>
Improving zero-shot learning by mitigating the hubness problem
<p>Data associated with the paper <a href="https://arxiv.org/pdf/1412.6568">Improving zero-shot learning by mitigating the hubness problem, </a>proceedings of ICLR 2015 (International Conference on Learning Representations), workshop track.</p> <p><strong>Abstract: </strong>The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels. We show that the neighbourhoods of the mapped elements are strongly polluted by hubs, vectors that tend to be near a high proportion of items, pushing their correct labels down the neighbour list. After illustrating the problem empirically, we propose a simple method to correct it by taking the proximity distribution of potential neighbours across many mapped vectors into account. We show that this correction leads to consistent improvements in realistic zero-shot experiments in the cross-lingual, image labeling and image retrieval domains.</p>
Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning
<p>Code used for the paper along with the generated outputs</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.