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.
82
datasets available to search
ShareScore release 0.9.0
Dataset results
82 results for “Adaptive Learning”
B3DB Dataset adapted for A Transparent Machine Learning Model To Understand Drugs Permeability Through the Blood Brain Barrier
<p>The B3DB dataset which we adapted for use for our paper "A Transparent Machine Learning Model To Understand Drugs Permeability Through the Blood Brain Barrier"</p>
Literacy-Adapted Psychosocial Treatments for Chronic Pain --- "Learning About Mastering/My Pain"
ClinicalTrials.gov study NCT01967342. IPD Sharing: YES. Countries: 1. Publications: 14.
Data for: Hierarchial motor adaptations negotiate failures during force field learning
Open the record for dataset details and reuse information.
Data from: Acoustic adaptation to city noise through vocal learning by a songbird
Open the record for dataset details and reuse information.
Social learning by mate-choice copying increases dispersal and reduces local adaptation
Open the record for dataset details and reuse information.
Data from: Machine learning based detection of adaptive divergence of the stream mayfly Ephemera strigata populations
Open the record for dataset details and reuse information.
Data for: Exploration-based learning of a stabilizing controller predicts locomotor adaptation
Open the record for dataset details and reuse information.
Competitive advantage of rare behaviors induces adaptive diversity rather than social conformity in skill learning
<p><span>Recent studies have emphasized the role of social learning and cultural transmission in promoting conformity and uniformity in animal groups, but little attention has been given to the role of negative frequency-dependent learning in impeding conformity and promoting diversity instead. Here we show experimentally that under competitive conditions, that are common in nature, social foragers (although capable of social learning) are likely to develop diversity in foraging specialization rather than uniformity. Naïve house sparrows that were introduced into groups of foraging specialists did not conform to the behaviour of the specialists but, rather, learned to use the alternative food-related cues, thus forming groups of complementary specialists. We further show that individuals in such groups may forage more effectively in diverse environments. Our results suggest that when the benefit from socially acquired skills diminishes through competition in a negative frequency-dependent manner, animal societies will become behaviourally diverse rather than uniform.</span></p>
Data from: Evolutionary online behaviour learning and adaptation in real robots
Online evolution of behavioural control on real robots is an open-ended approach to autonomous learning and adaptation: robots have the potential to automatically learn new tasks and to adapt to changes in environmental conditions, or to failures in sensors and/or actuators. However, studies have so far almost exclusively been carried out in simulation because evolution in real hardware has required several days or weeks to produce capable robots. In this article, we successfully evolve neural network-based controllers in real robotic hardware to solve two single-robot tasks and one collective robotics task. Controllers are evolved either from random solutions or from solutions pre-evolved in simulation. In all cases, capable solutions are found in a timely manner (1 h or less). Results show that more accurate simulations may lead to higher-performing controllers, and that completing the optimization process in real robots is meaningful, even if solutions found in simulation differ from solutions in reality. We furthermore demonstrate for the first time the adaptive capabilities of online evolution in real robotic hardware, including robots able to overcome faults injected in the motors of multiple units simultaneously, and to modify their behaviour in response to changes in the task requirements. We conclude by assessing the contribution of each algorithmic component on the performance of the underlying evolutionary algorithm.
Dataset for a physics informed deep learning method with adaptively weighted loss for modeling soil water flows
<p>The data for the 11 scenarios generated by Hydrus-1D is located in data.zip</p> <p>The code for the physics-informed neural networks with adaptively weighted loss used to simulate water flow in loam soils is located at PINN_adaptively_weighted_loss_loam.zip</p>
Image-based taxonomic classification of bulk biodiversity samples using deep learning and domain adaptation
<p>Complex bulk samples of insects from biodiversity surveys present a challenge for taxonomic identification, which could be overcome by high-throughput imaging combined with machine learning for rapid classification of specimens. These procedures require that taxonomic labels from an existing source data set are used for model training and prediction of an unknown target sample. However, such transfer learning may be problematic for the study of new samples not previously encountered in an image set, e.g. from unexplored ecosystems, and require methods of domain adaptation that reduce the differences in the feature distribution of the source and target domains (training and test sets). We assessed the efficiency of domain adaptation for family-level classification of bulk samples of Coleoptera, as a critical first step in the characterisation of biodiversity samples. Neural network models trained with images from a global database of Coleoptera were applied to a biodiversity sample from understudied forests in Cyprus as the target. Within-dataset classification accuracy reached 98% and depended on the number and quality of training images and on dataset complexity. The accuracy of between-datasets predictions (across disparate source-target pairs that do not share any species or genera) was at most 82% and depended greatly on the standardisation of the imaging procedure. Algorithms for domain adaptation significantly improved the prediction performance of models trained by non-standardised, low-quality images. Our findings demonstrate that existing databases can be used to train models and successfully classify images from unexplored biota, but the imaging conditions and classification algorithms need careful consideration.</p>
Dataset & Code related to article 'Bilateral Adaptive Graph Convolutional Network on CT based COVID-19 Diagnosis with Uncertainty-Aware Consensus-Assisted Multiple Instance Learning'
<p>This record contains the 7768 lung masks <strong>manual annotations, implementation code, and pre-trained models</strong> related to the article 'Bilateral Adaptive Graph Convolutional Network on CT based COVID-19 Diagnosis with Uncertainty-Aware Consensus-Assisted Multiple Instance Learning'</p> <p>Also we include the visualised, selected top D reliable CT slices for all COVID-19 patients in the test dataset for better understanding. </p> <p>For the detailed usage of the data and code, please refer to https://github.com/smallmax00/BAGCN-Covid19</p> <p> </p>
The P3 event-related potential increases when humans learn a strategy for motor adaptation
<p>This publication contains the raw EEG and kinematics datasets along with the PCA solutions for experiments 1 and 2 presented in the manuscript entitled The <em>P3 event-related potential increases when humans learn a strategy for motor adaptation</em> by Betina Korka and Max-Philipp Stenner.</p>
Ripple: A Long-Sighted Self-Adaptation Approach to Retrain Machine-Learning-Enabled Systems
<p>Data files required to reproduce the results of paper "Ripple: A Long-Sighted Self-Adaptation Approach to Retrain Machine-Learning-Enabled Systems" submitted to ICSME 2025</p>
Dataset for: Sky pixel detection in outdoor imagery using an adaptive algorithm and machine learning.
<p>The data presented in this article is related to the research article entitled ``Sky pixel detection in outdoor imagery using an adaptive algorithm and machine learning." \citep{Nice2019UC}.</p> <p>The dataset consists of a trained Inception V3 neural network model as well as the configuration files to train the neural network and run the inferences. The dataset also contains two sets of outdoor imagery (from Skyfinder and Google Street View) used to train the neural network and validate the sky pixel detection system in the linked article. The original images are included as well as rescaled imagery used to train the neural network, and sky masks used for validation.</p>
MD simulations files for: Enhanced Sampling of Biomolecular Slow Conformational Transitions Using Adaptive Sampling and Machine Learning
<p>Here's a rephrased version of the README file:</p> <p>#### Enhanced Sampling of Biomolecular Slow Conformational Transitions Using Adaptive Sampling and Machine Learning</p> <p>**Authors:** Mingyuan Zhang, Hao Wu, Yong Wang</p> <p>This repository contains the official implementation for the paper "Enhanced Sampling of Biomolecular Slow Conformational Transitions Using Adaptive Sampling and Machine Learning" by Mingyuan Zhang, Hao Wu, and Yong Wang. Included are all trajectories from our MD simulations in the form of PLUMED COLVAR files, as well as all analysis scripts and files needed to replicate the results and figures presented in both the main text and Supporting Information (SI) of the paper.</p> <p>The paper features two examples: Ala2 and Ala10. For each, we have organized all the associated simulation files as they were during our automated simulation pipeline. The directory structure is the same for both examples. Here, we use Ala2, found in the `Ala2` folder, as an example:</p> <p>### Key Components</p> <p>- **Automated Pipeline Implementation:** The pipeline is implemented in `Ala2/7-adaptive-40ps/ala2.ipynb`. This implementation is ready to use once all required packages are installed, and gmx/gmx_mpi/plumed are callable within the notebook. After configuring the environment and specifying parameters like `gpu_id`, `ntomp`, and `n_sim` according to your hardware, running the blocks will replicate the entire pipeline.</p> <p>- **Analysis Scripts:** The scripts to replicate the results or figures from the main text or SI are organized in three files: `Ala2/7-adaptive-40ps/AdaptiveSamplingAnalysis.ipynb`, `Ala2/7-adaptive-40ps/compare_with_msm.ipynb`, and `Ala2/7-adaptive-40ps/opes/COLVAR/analysis.ipynb`.</p> <p>### Directory Structure</p> <p>Under the `Ala2` main directory, there are seven subdirectories:</p> <p>- **`Ala2/1-topol/`**: Contains files generated during system construction, including the final Gromacs topology file `topol.top`, which is necessary for running the automated simulation script.</p> <p>- **`Ala2/2-em/`, `Ala2/3-nvt/`, `Ala2/4-npt/`**: These directories store files generated during energy minimization and NVT/NPT equilibration. The `Ala2/4-npt/npt.gro` file is required to run the automated simulation script.</p> <p>- **`Ala2/mdp/`**: Contains all mdp files used, including `Ala2/mdp/md_detail.mdp`, which is necessary for running the automated simulation script.</p> <p>- **`Ala2/7-adaptive-40ps/`**: Contains all simulation and analysis scripts, along with files required to replicate the study related to the automated pipeline.</p> <p> 1. **`Ala2/7-adaptive-40ps/CV/`**: Stores all COLVAR files from adaptive sampling simulations.<br> <br> 2. **`Ala2/7-adaptive-40ps/opes/`**: Contains all files related to OPES simulations, including raw data for the final FES plots found in `Ala2/7-adaptive-40ps/opes/COLVAR/`. The script for replicating OPES and FES estimation figures is located in `Ala2/7-adaptive-40ps/opes/COLVAR/analysis.ipynb`.<br> <br> 3. **`Ala2/7-adaptive-40ps/figures/`**: Includes all original figures from the main text and SI, saved at 600 dpi.<br> <br> 4. **`Ala2/7-adaptive-40ps/traj_and_dat/`**: Stores all PLUMED `*.dat` files for the `DRIVER` utility in adaptive sampling simulations, a topology file `input.pdb` for PLUMED `MOLINFO`, and a topology file `seed_ref.pdb` for MDAnalysis adaptive sampling seed `*.gro` generation. Note that all `*.xtc` files from adaptive sampling were deleted to reduce the package size.<br> <br> 5. **Seed Index Files:** Seed indices for each round are stored as `Ala2/7-adaptive-40ps/round{i}_seed.txt`, necessary for figure replication.<br> <br> 6. **Automated Pipeline Notebook:** Implemented in `Ala2/ala2.ipynb`. Ensure that all imported packages are installed and gromacs (both gmx and gmx_mpi)/plumed can be called within the Jupyter notebook.<br> <br> 7. **Adaptive Sampling Analysis:** Scripts for analyzing adaptive sampling trajectories are found in `Ala2/AdaptiveSamplingAnalysis.ipynb`. This notebook contains scripts to replicate all figures related to adaptive sampling.<br> <br> 8. **MSM Comparison:** Analysis scripts for MSM comparison are located in `Ala2/compare_with_msm.ipynb`. This notebook contains scripts to replicate figures used for MSM/OPES comparison.</p> <p>- **`Ala2/8-adaptive-400ps/`**: Contains all simulation files (except xtc) for an additional adaptive sampling dataset computed for MSM comparison.</p> <p>### Contact Information</p> <p>We are continuing to test and improve the pipeline, so a tutorial is not yet available. Please feel free to reach out with any questions related to the implementation via email at mingyuanzhang@zju.edu.cn or by raising an issue on our GitHub page: https://github.com/yongwangCPH/papers/tree/main/2024/ALICE.</p>
DYNAMIC PRICING IN FINANCIAL TECHNOLOGY: EVALUATING MACHINE LEARNING SOLUTIONS FOR MARKET ADAPTABILITY
<p>The rapid advancement of technology has transformed the financial services sector, leading to the rise of fintech companies that leverage cutting-edge tools such as artificial intelligence (AI) and machine learning (ML) to offer innovative solutions. One area where fintech is particularly impactful is dynamic pricing, which involves adjusting prices in real-time based on market conditions, user behavior, and external factors. The ability to optimize pricing in response to fluctuating conditions is critical for maximizing profitability, improving customer satisfaction, and maintaining competitiveness. In this context, machine learning algorithms provide a powerful framework for making data-driven pricing decisions by learning from historical data and predicting future trends.</p>
Olfactory Learning Supports an Adaptive Sugar-Aversion Gustatory Phenotype in the German Cockroach
<p>An association of food sources with odors prominently guides foraging behavior in animals. To understand the interaction of olfactory memory and food preferences, we used glucose-averse (GA) German cockroaches. Multiple populations of cockroaches evolved a gustatory polymor-phism where glucose is perceived as a deterrent and enables GA cockroaches to avoid eating glucose-containing toxic baits. Comparative behavioral analysis using an operant conditioning paradigm revealed that learning and memory guide foraging decisions. Cockroaches learned to associate specific food odors with fructose (phagostimulant, reward) within only 1 hr of condi-tioning session, and with caffeine (deterrent, punishment) after only three 1 hr conditioning ses-sions. Glucose acted as reward in wild type (WT) cockroaches, but GA cockroaches learned to avoid an innately attractive odor that was associated with glucose. Olfactory memory was retained for at least 3 days after three 1 hr conditioning sessions. Our results reveal that specific tastants can serve as potent reward or punishment in olfactory associative learning, which reinforces gustatory food preferences. Olfactory learning therefore reinforces behavioral resistance of GA cockroaches to sugar-containing toxic baits. Cockroaches may also generalize their olfactory learning to baits that contain the same or similar attractive odors even if they do not contain glucose.</p>
Analysis and Data of "Adaptive tuning of human learning and choice variability to unexpected uncertainty"
<p>Data and analysis scripts in "Adaptive tuning of human learning and choice variability to unexpected uncertainty". See https://github.com/jlexternal/RLVOLUNP_ana for directory structure. </p>
Adaptation and evolution of teaching method for university programming subject to the online learning environment - Commit Data
<p>This dataset contains commit UNIX timestamps for Copymaster assignment git repositories of students studying Operating Systems class at Technical University of Košice in the span of years 2017/2018 - 2020/2021.</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.