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”
Figure 5 in Hybrid neural network with genetic algorithms for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumbers field of Ramhormoz, Iran
Figure 5. Tetranychus urticae distribution maps in actual (b, d and f) and classified conditions by MLPNN (c, e and a). The maps of a, c, e and b, d, f have been drawn according to economic threshold of 4, 8 and 12, respectively.
Data and code for article "Nature reserve customized method of photo and video camera traps materials processing using two-stage neural network approach"
<p><strong>DESCRIPTION</strong> 📓</p> <p>"data" folder directory contains the datasets for classification and detection. </p> <ol> <li>The detection dataset has <strong>YOLOv5 format</strong> and contains three classes <strong>[tigers, leopards, empty]</strong>. The class empty is about <strong>10%</strong> of the total data. The leopard and tiger classes contain <strong>3500</strong> images each. The entire amount of data for the detection task is <strong>7600</strong> images.</li> <li>The classification dataset contains two classes <strong>[tigers, leopards]</strong>. Images for classification are cropped images from the detection task using bounding boxes. Each class has <strong>3500</strong> images</li> </ol> <p> </p> <p>The "weights" folder contains pretrained models for classification and detection tasks. </p> <ul> <li>The detector weights were pre-trained on <strong>231k</strong> images from camera traps located throughout Russia.</li> <li>The classifier weights were pre-trained on <strong>416k</strong> images that were cropped with <strong>bounding boxes</strong> from photographs for the detection task. Some of the images for the classification task were taken from the <strong>Internet</strong>. The classifiers were trained for <strong>29 classes</strong>.</li> <li>You can also find folder <strong>tigers_vs_leopards</strong> in both the detection and classification directory, where there are weights that have been trained on a part of the camera trap images available at the link below.</li> </ul> <p><em>Classification weights</em></p> <ol> <li>EfficientNetv2-M</li> <li><strong>ResNeSt-101e</strong> (🚀 RECOMMENDED)</li> <li>ResNet-101d</li> <li>ReXnet-100</li> <li>SeResNet-152d</li> </ol> <p><em>Detection weights</em></p> <ol> <li>YOLOR-W6-1280</li> <li>YOLOX-X-640</li> <li>YOLOv5-X-640</li> <li>YOLOv5-X-1280</li> <li>YOLOv5-M6-1280</li> <li><strong>YOLOv5-L6-1280</strong> (🚀 RECOMMENDED)</li> </ol> <p>Read README.md file for more details</p>
Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks
<p>Classification dataset used in Kosiba et al. 2020 (10.1093/mnras/staa1723) consisting of candidate clusters in the XCLASS survey</p> <p>Training and testing images and corresponding labels low-z (clusters, 0<z<0.3), hi-z (clusters, z>0.3), nearby galaxy, point source (point, double source, star/AGN), and other (artefact, edge)</p>
Data from: Prediction of Pedestrian Speed with Artificial Neural Networks
<p>Corridor data are trajectories of pedestrians in a closed corridor of lenght 30m and width 1.8m. The trajectories are measured on a section of length 6m. Experiments are carried out with N=15, 30, 60, 85, 95, 110, 140 and 230 participants.</p> <p>Bottleneck data are trajectories of pedestrian in a bottleneck of lenght 8m and width 1.8m. Experiments are carried out with 150 participants for bottleneck widths w=0.7, 0.95 1.2 and 1.8m.</p> <p>See http://ped.fz-juelich.de/experiments/2009.05.12_Duesseldorf_Messe_Hermes/docu/VersuchsdokumentationHERMES.pdf page 20 and 24 for details (in German). The data are part of the online database http://ped.fz-juelich.de/database.</p> <p>Column names of the file are: ID FRAME X Y Z.</p> <ul> <li>ID is the pedestrian ID.</li> <li>FRAME is the frame number (frame rate is 1/16s).</li> <li>X Y and Z are pedestrian position in 3D.</li> </ul>
Figure 3. Neural network representation for HMM given in Figure 2.-Neuroevolution Mechanism for Hidden Markov Model
<p>In our proposed structure, we injected a hidden layer to have a multilayer perceptron which<br> is more efficient than single layer perceptron.<br> To make this process clear, Figure 3 shows the neural networks for the HMM presented in<br> Figure 2.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 14. Number of artificial creatures that could survive in the external environment
<p>Artificial creatures and the virtual environment are designed and implemented in a C++ platform in which simulations are performed. In the GA algorithm, at First step a population of 100 complex artificial creatures that each of them had 150 neurons were tested and evaluated by GA; each neuron connected to 15 post-synaptic neurons with different axonal conduction delays between every two neurons. In every generation fitness function has been calculated for all population. The initial energy level for each creature is considered as 50. Figure 14 the number of survived chromosome increases with<br> generation progressing.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 11. Crossover with two cut points
<p>Then next generation are produced by combination of the elites (15%), crossover (55%) and mutation (30%) of the initial population. Elites are the best chromosomes which are directly transferred to the next generation. Because of long chromosome length, for crossover, five points are randomly chosen in each parent as cut points. Figure 11 shows a typical crossover with two cut points and Figure 12 illustrates a flowchart for the proposed evolutionary model. Selections are based on Roulette Wheel selection, more detailed information can be found in.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 10: A typical neuron and postsynaptic connections with weights and delays
<p>First, an initial random population of creatures is generated where the neural networks of the creatures are coded as chromosomes, as shown in Figure 10a and Figure 10b. Each chromosome consists of four parts: A1, A2, A3 and A4. Each part consists of N segments for N neurons of a typical neural network structure. The first part, A1, denotes a, b, c and d parameters of neurons Izhikevich model (discussed in (1) and (2)). Each segment of A2 shows postsynaptic weights and connections for corresponding neuron and each segment of A3 indicates postsynaptic delays of theconnections. Segment A4 shows postsynaptic neurons that are connected to corresponding neuron, as shown in Figure 10b.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 5. The periphery of circular area around of artificial creature in each position
<p>It is assumed in the simulation that the artificial creature in each location stands in the center of a circular area with a radius of its vision range, i.e. 2 meters. If the creature turns around itself; it only can see objects in its visual range. When a food object appears in the periphery of this circular area, a creature should find this food. Moving around, another food appears in a random place on periphery of the circular area, and this procedure repeat for 5 iterations. As shown in Figure 5 the periphery of the circular area around the artificial creature in each position is divided to 48 slots, which can be considered as a rectangular. In the simulation program it is implemented as an array of 48 × 3.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 2. Example of different axonal conduction delay between presynaptic neuron A0 and postsynaptic neuron A1 and A2
<p>Different axonal conduction delays between every two neurons are applied as follows:<br> For instance, consider presynaptic neuron A0 and postsynaptic neurons A1 and A2 in Figure 2. If neuron A0 fires spike S0 in t = 9 and S1 in t = 11 and with a time step equal to 0.5 ms, S0 arrives to A1 in t = 13 and to A2 in t = 14 where S1 arrives to A1 in t = 15 and to A2 in t = 16. This is implemented using counters assigned to each spike which increases with each time step in the time window. If counters arrive to axonal delay values, the effect of spikes from presynaptic neuron applies to the post synaptic neurons.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 8. Flowchart for movements of creature
<p>Window time has a fixed length between and and is an appropriate time interval [5]. So in each time window the total number of spikes in each three neurons is compared with other three neurons and artificial creature moves toward direction that the respective neurons fired maximum number of spikes. These fixed time<br> windows consist of 600 time-steps. Each time step is 0.5 ms. Flowchart in Figure 8 shows details.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 1. Typical neural networks SYNAPTIC
<p>A reservoir network has been used in this paper. This structure has been shown in Figure 1.<br> As is observable this network has two input and output layers. The neuronal network that have been<br> used is composed of N = 150 randomly connected Izhikevich spiking neurons and different axonal<br> conduction delays between each two neurons. Information is transferred between neurons of the<br> networks through the links between every two neurons representing synapses. Each neuron is<br> connected to M = 15 random neurons, so that the probability of connection is M / N = 0.15. It is<br> noticeable that in this network, not only the connection between two neurons is random, but also the<br> neurons type selection is random, too.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 13. Average fitness at generation progressing
<p>Figure 13 compares the average fitness at generations in one typical program running. As can be seen from this figure, the average of fitness grows as the number of generations increases.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 7. Effect of different type of movement on the image in the vision of artificial creature.
<p>Figure 7a, Figure 7b, Figure 7c and Figure 7d, shows effect of different type of movement on the image in the vision of artificial creature if food be on vision boundaries. As mentioned each part of the image equal 7.5 degree.<br> Therefore 15 degree left or right rotation locomotion equivalent two parts shift toward left or right.<br> For motion to forward direction, size of the image has been reduplicated so that each part has been become to the two similar parts. Then half of new image in right side and left side has been deleted in order to create new close image in vision. Accordingly, if food be on vision boundaries, the number of black parts of the image for the food object in ultimate location is 2, by one movement to forward direction the number of these parts become to 4, by one movement to forward direction the number of these parts become to 8 and so on. After four movements to forward all part of the image is black and the creature is succeed find the food object.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 6, One image in sight of artificial creature.
<p>Figure 6 shows an image in sight of the creature, where the food in this image is the dark part of the vision. If the food object places in the vision edge of the artificial creature (2 meters), two squares in the image in sight of the creature becomes black and by getting the artificial creature closer to the food, more squares of image in sight become block and if all parts of the image in sight of the creature become black, the artificial creature has been successful in finding the food object. In Figure 6 each part of the image divided to 3 subparts because 3 neurons per part of image in the input layer of the artificial creature network (vision) have been considered. So vision of the artificial creature composed of 60 neurons due to:</p> <p>For each black part of image in sight of the artificial creature, three signals as the input signals is applied to the three respective neurons.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 9. A typical artificial life form and circular area around of it
<p>As mentioned the reservoir neural network has been chosen for neural network of the artificial creature as main body structure. Figure 9 illustrates a typical artificial life form and circular area around of it. Maximum seeing of the artificial life form is periphery of the circular area and can't see places that have beyond of periphery of the circular area. The artificial creature by each movement is the center of a circular area so if the creature move to forward direct can see new<br> places and some places are voided of seeing.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 12. Genetic Algorithm flowchart
<p>Then next generation are produced by combination of the elites (15%), crossover (55%) and mutation (30%) of the initial population. Elites are the best chromosomes which are directly transferred to the next generation. Because of long chromosome length, for crossover, five points are randomly chosen in each parent as cut points. Figure 11 shows a typical crossover with two cutpoints and Figure 12 illustrates a flowchart for the proposed evolutionary model. Selections are based on Roulette Wheel selection, more detailed information can be found in.</p>
BRAIN Journal-Artificial Neuron Modelling Based on Wave Shape-Figure 1. Typical feedforward artificial neural network processing unit
<p>In Figure 1, each input X is weighted by a separate weight value w. These are then summed together to give a total input value for the neuron. This total can then be passed through a function, to transform it into the desired output value. This is then compared to the actual output value d; where the error or differences between the two sets is measured and used to correct the weight<br> values, to bring the two sets of values closer. One way to update the weights is after each individual pattern is presented and processed. Another option is to process the error after the presentation of the whole dataset, as part of a batch update.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 4: Pseudo code for applying different axonal conduction delay between presynaptic neurons and postsynaptic neurons
<p>In each time step, axonal conduction delays between presynaptic neurons and postsynaptic neurons are examined whether they are equal to the elements of array I_S, to apply the respective spikes.<br> The pseudo code for applying different axonal conduction delay between presynaptic neurons and postsynaptic neurons are shown in Figure 4.</p>
BRAIN Journal-Evolving Spiking Neural Networks for Control of Artificial Creatures-Figure 15. Movements a typical successful creature to find food
<p>Figure 15 (a, b, c, d, e, f, g, h) illustrates movements of a typical successful creature for finding one food object.</p> <p>We believe that this study can be a step forward in understanding the morphology of artificial creatures. Also this paper suggests more complex artificial life examination by adding different part to these networks similar to different segments of the brain such as: vision, locomotion, hippocampus and communication in a future work. Because of the different axonal conduction delay between every two neurons in the neural network of artificial creatures in this paper, our next study is to enhance the artificial lives by STDP learning.</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.