Damage identification for large span structure based on multiscale inputs to artificial neural networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Lu W
PROVIDER: S-EPMC4058217 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Optoelectronic neural networks (ONN) are a promising avenue in AI computing due to their potential for parallelization, power efficiency, and speed. Diffractive neural networks, which process information by propagating encoded light through trained optical elements, have garnered interest. However, training large-scale diffractive networks faces challenges due to the computational and memory costs of optical diffraction modeling. Here, we present DANTE, a dual-neuron optical-artificial learning architecture. Optical neurons model the optical diffraction, while artificial neurons approximate the intensive optical-diffraction computations with lightweight functions. DANTE also improves convergence by employing iterative global artificial-learning steps and local optical-learning steps. In simulation experiments, DANTE successfully trains large-scale ONNs with 150 million neurons on ImageNet, previously unattainable, and accelerates training speeds significantly on the CIFAR-10 benchmark compared to single-neuron learning. In physical experiments, we develop a two-layer ONN system based on DANTE, which can effectively extract features to improve the classification of natural images.
| S-EPMC10625607 | biostudies-literature
Project description:Solid matter that can rapidly and reversibly switch between adhesive and non-adhesive states is desired in many technological domains including climbing robotics, actuators, wound dressings, and bioelectronics due to the ability for on-demand attachment and detachment. For most types of smart adhesive materials, however, reversible switching occurs only at narrow scales (nanoscale or microscale), which limits the realization of interchangeable surfaces with distinct adhesive states. Here, we report the design of a switchable adhesive hydrogel via dynamic multiscale contact synergy, termed as DMCS-hydrogel. The hydrogel rapidly switches between slippery (friction ~0.04 N/cm2) and sticky (adhesion ~3 N/cm2) states in the solid-solid contact process, exhibits large span, is switchable and dynamic, and features rapid adhesive switching. The design strategy of this material has wide applications ranging from programmable adhesive materials to intelligent devices.
| S-EPMC9666504 | biostudies-literature
Project description:Our cognition relies on the ability of the brain to segment hierarchically structured events on multiple scales. Recent evidence suggests that the brain performs this event segmentation based on the structure of state-transition graphs behind sequential experiences. However, the underlying circuit mechanisms are poorly understood. In this paper we propose an extended attractor network model for graph-based hierarchical computation which we call the Laplacian associative memory. This model generates multiscale representations for communities (clusters) of associative links between memory items, and the scale is regulated by the heterogenous modulation of inhibitory circuits. We analytically and numerically show that these representations correspond to graph Laplacian eigenvectors, a popular method for graph segmentation and dimensionality reduction. Finally, we demonstrate that our model exhibits chunked sequential activity patterns resembling hippocampal theta sequences. Our model connects graph theory and attractor dynamics to provide a biologically plausible mechanism for abstraction in the brain.
| S-EPMC8412329 | biostudies-literature
Project description:BackgroundStudies in mothers of Down syndrome individuals (MDS) point to a role for polymorphisms in folate metabolic genes in increasing chromosome damage and maternal risk for a Down syndrome (DS) pregnancy, suggesting complex gene-gene interactions. This study aimed to analyze a dataset of genetic and cytogenetic data in an Italian group of MDS and mothers of healthy children (control mothers) to assess the predictive capacity of artificial neural networks assembled in TWIST system in distinguish consistently these two different conditions and to identify the variables expressing the maximal amount of relevant information to the condition of being mother of a DS child.The dataset consisted of the following variables: the frequency of chromosome damage in peripheral lymphocytes (BNMN frequency) and the genotype for 7 common polymorphisms in folate metabolic genes (MTHFR 677C>T and 1298A>C, MTRR 66A>G, MTR 2756A>G, RFC1 80G>A and TYMS 28bp repeats and 1494 6bp deletion). Data were analysed using TWIST system in combination with supervised artificial neural networks, and a semantic connectivity map.ResultsTWIST system selected 6 variables (BNMN frequency, MTHFR 677TT, RFC1 80AA, TYMS 1494 6bp +/+, TYMS 28bp 3R/3R and MTR 2756AA genotypes) that were subsequently used to discriminate between MDS and control mothers with 90% accuracy. The semantic connectivity map provided important information on the complex biological connections between the studied variables and the two conditions (being MDS or control mother).ConclusionsOverall, the study suggests a link between polymorphisms in folate metabolic genes and DS risk in Italian women.
| S-EPMC2949778 | biostudies-literature
Project description:An open challenge on the road to unraveling the brain's multilevel organization is establishing techniques to research connectivity and dynamics at different scales in time and space, as well as the links between them. This work focuses on the design of a framework that facilitates the generation of multiscale connectivity in large neural networks using a symbolic visual language capable of representing the model at different structural levels-ConGen. This symbolic language allows researchers to create and visually analyze the generated networks independently of the simulator to be used, since the visual model is translated into a simulator-independent language. The simplicity of the front end visual representation, together with the simulator independence provided by the back end translation, combine into a framework to enhance collaboration among scientists with expertise at different scales of abstraction and from different fields. On the basis of two use cases, we introduce the features and possibilities of our proposed visual language and associated workflow. We demonstrate that ConGen enables the creation, editing, and visualization of multiscale biological neural networks and provides a whole workflow to produce simulation scripts from the visual representation of the model.
| S-EPMC8777257 | biostudies-literature
Project description:MotivationMany types of omics data are compiled as lists of connections between elements and visualized as networks or graphs where the nodes and edges correspond to the elements and the connections, respectively. However, these networks often appear as 'hair-balls'-with a large number of extremely tangled edges-and cannot be visually interpreted.ResultsWe present an interactive, multiscale navigation method for biological networks. Our approach can automatically and rapidly abstract any portion of a large network of interest to an immediately interpretable extent. The method is based on an ultrafast graph clustering technique that abstracts networks of about 100 000 nodes in a second by iteratively grouping densely connected portions and a biological-property-based clustering technique that takes advantage of biological information often provided for biological entities (e.g. Gene Ontology terms). It was confirmed to be effective by applying it to real yeast protein network data, and would greatly help modern biologists faced with large, complicated networks in a similar manner to how Web mapping services enable interactive multiscale navigation of geographical maps (e.g. Google Maps).AvailabilityJava implementation of our method, named NaviCluster, is available at http://navicluster.cb.k.u-tokyo.ac.jp/.Contactthanet@cb.k.u-tokyo.ac.jpSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC3072549 | biostudies-literature
Project description:Artificial neural networks (ANNs) are processors that are trained to perform particular tasks. We couple a computational ANN with a simulated affective system in order to explore the interaction between the two. In particular, we design a simple affective system that adjusts the threshold values in the neurons of our ANN. The aim of this paper is to demonstrate that this simple affective system can control the firing rate of the ensemble of neurons in the ANN, as well as to explore the coupling between the affective system and the processes of long term potentiation (LTP) and long term depression (LTD), and the effect of the parameters of the affective system on its performance. We apply our networks with affective systems to a simple pole balancing example and briefly discuss the effect of affective systems on network performance.
| S-EPMC3841186 | biostudies-literature
Project description:A significant amount of attention has been given to the design and synthesis of co-crystals by both industry and academia because of its potential to change a molecule's physicochemical properties. Yet, difficulties arise when searching for adequate combinations of molecules (or coformers) to form co-crystals, hampering the efficient exploration of the target's solid-state landscape. This paper reports on the application of a data-driven co-crystal prediction method based on two types of artificial neural network models and co-crystal data present in the Cambridge Structural Database. The models accept pairs of coformers and predict whether a co-crystal is likely to form. By combining the output of multiple models of both types, our approach shows to have excellent performance on the proposed co-crystal training and validation sets, and has an estimated accuracy of 80 % for molecules for which previous co-crystallization data is unavailable.
| S-EPMC7756866 | biostudies-literature
Project description:Industry 4.0 is all about interconnectivity, sensor-enhanced process control, and data-driven systems. Process analytical technology (PAT) such as online nuclear magnetic resonance (NMR) spectroscopy is gaining in importance, as it increasingly contributes to automation and digitalization in production. In many cases up to now, however, a classical evaluation of process data and their transformation into knowledge is not possible or not economical due to the insufficiently large datasets available. When developing an automated method applicable in process control, sometimes only the basic data of a limited number of batch tests from typical product and process development campaigns are available. However, these datasets are not large enough for training machine-supported procedures. In this work, to overcome this limitation, a new procedure was developed, which allows physically motivated multiplication of the available reference data in order to obtain a sufficiently large dataset for training machine learning algorithms. The underlying example chemical synthesis was measured and analyzed with both application-relevant low-field NMR and high-field NMR spectroscopy as reference method. Artificial neural networks (ANNs) have the potential to infer valuable process information already from relatively limited input data. However, in order to predict the concentration at complex conditions (many reactants and wide concentration ranges), larger ANNs and, therefore, a larger training dataset are required. We demonstrate that a moderately complex problem with four reactants can be addressed using ANNs in combination with the presented PAT method (low-field NMR) and with the proposed approach to generate meaningful training data. Graphical abstract.
| S-EPMC7320049 | biostudies-literature
Project description:In this study, multilayer perceptron artificial neural networks are used to predict orthodontic treatment plans, including the determination of extraction-nonextraction, extraction patterns, and anchorage patterns. The neural network can output the feasibilities of several applicable treatment plans, offering orthodontists flexibility in making decisions. The neural network models show an accuracy of 94.0% for extraction-nonextraction prediction, with an area under the curve (AUC) of 0.982, a sensitivity of 94.6%, and a specificity of 93.8%. The accuracies of the extraction patterns and anchorage patterns are 84.2% and 92.8%, respectively. The most important features for prediction of the neural networks are "crowding, upper arch" "ANB" and "curve of Spee". For handling discrete input features with missing data, the average value method has a better complement performance than the k-nearest neighbors (k-NN) method; for handling continuous features with missing data, k-NN performs better than the other methods most of the time. These results indicate that the proposed method based on artificial neural networks can provide good guidance for orthodontic treatment planning for less-experienced orthodontists.
| S-EPMC6375961 | biostudies-literature