Search

Turbulence is still one of the main challenges in accurate prediction of reactive flows. Therefore, the development of new turbulence closures that can be applied to combustion problems is essential. Over the last few years, data-driven modeling has become popular in many fields as large, often extensively labeled datasets are now available and training of large neural networks has become possible on graphics processing units (GPUs) that speed up the learning process tremendously. However, the successful application of deep neural networks in fluid dynamics, such as in subfilter modeling in the context of large-eddy simulations (LESs), is still challenging. Reasons for this are the large number of degrees of freedom in natural flows, high requirements of accuracy and error robustness, and open questions, for example, regarding the generalization capability of trained neural networks in such high-dimensional, physics-constrained scenarios. This work presents a novel subfilter modeling approach based on a generative adversarial network (GAN), which is trained with unsupervised deep learning (DL) using adversarial and physics-informed losses. A two-step training method is employed to improve the generalization capability, especially extrapolation, of the network. The novel approach gives good results in a priori and a posteriori tests with decaying turbulence including turbulent mixing, and the importance of the physics-informed continuity loss term is demonstrated. The applicability of the network in complex combustion scenarios is furthermore discussed by employing it in reactive and inert LESs of the Spray A case defined by the Engine Combustion Network (ECN). [ABSTRACT FROM AUTHOR]

High-Performance Computing (HPC) has recently been attracting more attention in remote sensing applications due to the challenges posed by the increased amount of open data that are produced daily by Earth Observation (EO) programs. The unique parallel computing environments and programming techniques that are integrated in HPC systems are able to solve large-scale problems such as the training of classification algorithms with large amounts of Remote Sensing (RS) data. This paper shows that the training of state-of-the-art deep Convolutional Neural Networks (CNNs) can be efficiently performed in distributed fashion using parallel implementation techniques on HPC machines containing a large number of Graphics Processing Units (GPUs). The experimental results confirm that distributed training can drastically reduce the amount of time needed to perform full training, resulting in near linear scaling without loss of test accuracy. [ABSTRACT FROM AUTHOR]

An abstract of the article "Functional role of opponent, dopamine modulated D1/D2 plasticity in reinforcement learning" by Jenia Jitsev, Nobi Abraham, Abigail Morrison, and Marc Tittgemeyer is presented.

Introduction We here address the problem of integrating information about multiple objects and their positions on the visual scene. A primate visual system has little difficulty in rapidly achieving integration, given only a few objects. Unfortunately, computer vision still has great difficultly achieving comparable performance. It has been hypothesized that temporal binding or temporal separation could serve as a crucial mechanism to deal with information about objects and their positions in parallel to each other. Elaborating on this idea, we propose a neurally plausible mechanism for reaching local decision-making for "what" and "where" information to the global multi-object recognition. Mechanism The model we propose here is inspired by the binding-by-synchrony as well as the dynamic link architecture. The decision-making is done by so-called control (C) macrocolumn units, which are responsible not only for the synchronization or de-synchronization of selected feature macrocolumns, but also for signaling the position of the object in the scene. The feature macrocolumns are placed on two distinct domains. The input (I) domain contains the sensory data from the scene while the gallery (G) domain stores the reference objects to be recognized. Each macrocolumn consists of subunits called minicolumns, which are bound together by common afferents and lateral inhibition modulated by an autonomous oscillator of the integrate-and-fire (IF) type, being a further development of the previous modeling approach of a macrocolumn cortex. The binding-by-synchrony, establishing the related dynamic links, is achieved via similarity computation between the feature columns and the similarity-based modulation of a time constant and weight of the IF synaptic couplings, influenced by the C column subunits. Results Figure 1 demonstrates that the binding-by-synchrony in our system is achieved so rapidly within a few of hundred milliseconds. More precisely, the IF neural oscillators in the feature macrocolumns of I and G with the higher similarity become synchronized with zero-lag, showing asynchronous behavior between the IF oscillators of the feature macrocolumns with lower similarity. Transition of synchrony to asynchrony occurs by modulating a time constant and weight of the IF synaptic couplings, under the influence of subunit activities in the C. The zero-lag synchronization between the IF oscillators is the global object recognition, assigning each object the corresponding position in the scene, which is signaled by the activities in the C column units. [ABSTRACT FROM AUTHOR]

Our work deals with the self-organization of a memory structure that includes multiple hierarchical levels with massive recurrent communication within and between them. Such structure has to provide a representational basis for the relevant objects to be stored and recalled in a rapid and efficient way. Assuming that the object patterns consist of many spatially distributed local features, a problem of parts-based learning is posed. We speculate on the neural mechanisms governing the process of the structure formation and demonstrate their functionality on the task of human face recognition. The model we propose is based on two consecutive layers of distributed cortical modules, which in turn contain subunits receiving common afferents and bounded by common lateral inhibition (Figure 1). In the initial state, the connectivity between and within the layers is homogeneous, all types of synapses -- bottom-up, lateral and top-down -- being plastic. During the iterative learning, the lower layer of the system is exposed to the Gabor filter banks extracted from local points on the face images. Facing an unsupervised learning problem, the system is able to develop synaptic structure capturing local features and their relations on the lower level, as well as the global identity of the person at the higher level of processing, improving gradually its recognition performance with learning time. The structure formation relies on the activity-dependent bidirectional plasticity and the homeostatic regulation of unit's activity. While these occur on the slow time scale, the fast acting neural dynamics with strong competitive character ensures that only a small subset of units may update their synapses during a decision cycle spanned by oscillatory inhibition and excitation in the gamma range. This repetitive selection triggered by certain face images leads to amplification of the memory trace for the respective person. Acting together, homeostatic constraint and bidirectional plasticity work on reducing the overlap between different memory traces, segregating them in the memory structure. The ongoing modification of the memory's structure conditions the system for more and more coherent communication between the bottom-up and top-down signals. The binding of the local features via lateral and top-down connections into a global identity enhances the generalization capability of the memory, and renders the system to reliably recognize novel face images of different views not presented before. The proposed mechanisms of learning reveal thus basic principles behind the self-organization of successful subsystem coordination. [ABSTRACT FROM AUTHOR]

This work presents the development and implementation of a deep learning-based workflow for autonomous image analysis in nanoscience. A versatile, agnostic, and configurable tool was developed to generate instance-segmented imaging datasets of nanoparticles. The synthetic generator tool employs domain randomization to expand the image/mask pairs dataset for training supervised deep learning models. The approach eliminates tedious manual annotation and allows training of high-performance models for microscopy image analysis based on convolutional neural networks. We demonstrate how the expanded training set can significantly improve the performance of the classification and instance segmentation models for a variety of nanoparticle shapes, ranging from spherical-, cubic-, to rod-shaped nanoparticles. Finally, the trained models were deployed in a cloud-based analytics platform for the autonomous particle analysis of microscopy images., Competing Interests: The authors declare no competing financial interest., (© 2023 The Authors. Published by American Chemical Society.)

The rapidly growing use of imaging infrastructure in the energy materials domain drives significant data accumulation in terms of their amount and complexity. The applications of routine techniques for image processing in materials research are often ad hoc , indiscriminate, and empirical, which renders the crucial task of obtaining reliable metrics for quantifications obscure. Moreover, these techniques are expensive, slow, and often involve several preprocessing steps. This paper presents a novel deep learning-based approach for the high-throughput analysis of the particle size distributions from transmission electron microscopy (TEM) images of carbon-supported catalysts for polymer electrolyte fuel cells. A dataset of 40 high-resolution TEM images at different magnification levels, from 10 to 100 nm scales, was annotated manually. This dataset was used to train the U-Net model, with the StarDist formulation for the loss function, for the nanoparticle segmentation task. StarDist reached a precision of 86%, recall of 85%, and an F1-score of 85% by training on datasets as small as thirty images. The segmentation maps outperform models reported in the literature for a similar problem, and the results on particle size analyses agree well with manual particle size measurements, albeit at a significantly lower cost.

One of the most promising avenues for compiling connectivity data originates from the notion that individual brain regions maintain individual connectivity profiles; the functional repertoire of a cortical area ("the functional fingerprint") is closely related to its anatomical connections ("the connectional fingerprint") and, hence, a segregated cortical area may be characterized by a highly coherent connectivity pattern. Diffusion tractography can be used to identify borders between such cortical areas. Each cortical area is defined based upon a unique probabilistic tractogram and such a tractogram is representative of a group of tractograms, thereby forming the cortical area. The underlying methodology is called connectivity-based cortex parcellation and requires clustering or grouping of similar diffusion tractograms. Despite the relative success of this technique in producing anatomically sensible results, existing clustering techniques in the context of connectivity-based parcellation typically depend on several non-trivial assumptions. In this paper, we embody an unsupervised hierarchical information-based framework to clustering probabilistic tractograms that avoids many drawbacks offered by previous methods. Cortex parcellation of the inferior frontal gyrus together with the precentral gyrus demonstrates a proof of concept of the proposed method: The automatic parcellation reveals cortical subunits consistent with cytoarchitectonic maps and previous studies including connectivity-based parcellation. Further insight into the hierarchically modular architecture of cortical subunits is given by revealing coarser cortical structures that differentiate between primary as well as premotoric areas and those associated with pre-frontal areas.

Growing neuropsychological and neurophysiological evidence suggests that the visual cortex uses parts-based representations to encode, store and retrieve relevant objects. In such a scheme, objects are represented as a set of spatially distributed local features, or parts, arranged in stereotypical fashion. To encode the local appearance and to represent the relations between the constituent parts, there has to be an appropriate memory structure formed by previous experience with visual objects. Here, we propose a model how a hierarchical memory structure supporting efficient storage and rapid recall of parts-based representations can be established by an experience-driven process of self-organization. The process is based on the collaboration of slow bidirectional synaptic plasticity and homeostatic unit activity regulation, both running at the top of fast activity dynamics with winner-take-all character modulated by an oscillatory rhythm. These neural mechanisms lay down the basis for cooperation and competition between the distributed units and their synaptic connections. Choosing human face recognition as a test task, we show that, under the condition of open-ended, unsupervised incremental learning, the system is able to form memory traces for individual faces in a parts-based fashion. On a lower memory layer the synaptic structure is developed to represent local facial features and their interrelations, while the identities of different persons are captured explicitly on a higher layer. An additional property of the resulting representations is the sparseness of both the activity during the recall and the synaptic patterns comprising the memory traces.