Search

Abstract The majority of soccer analysis studies investigates specific scenarios through the implementation of computational techniques, which involve the examination of either spatiotemporal position data (movement of players and the ball on the pitch) or event data (relating to significant situations during a match). Yet, only a few applications perform a joint analysis of both data sources despite the various involved advantages emerging from such an approach. One possible reason for this is a non-systematic error in the event data, causing a temporal misalignment of the two data sources. To address this problem, we propose a solution that combines the SwiftEvent online algorithm (Gensler and Sick in Pattern Anal Appl 21:543–562, 2018) with a subsequent refinement step that corrects pass timestamps by exploiting the statistical properties of passes in the position data. We evaluate our proposed algorithm on ground-truth pass labels of four top-flight soccer matches from the 2014/15 season. Results show that the percentage of passes within half a second to ground truth increases from 14 to 70%, while our algorithm also detects localization errors (noise) in the position data. A comparison with other models shows that our algorithm is superior to baseline models and comparable to a deep learning pass detection method (while requiring significantly less data). Hence, our proposed lightweight framework offers a viable solution that enables groups facing limited access to (recent) data sources to effectively synchronize passes in the event and position data.

The analysis of news dissemination is of utmost importance since the credibility of information and the identification of disinformation and misinformation affect society as a whole. Given the large amounts of news data published daily on the Web, the empirical analysis of news with regard to research questions and the detection of problematic news content on the Web require computational methods that work at scale. Today's online news are typically disseminated in a multimodal form, including various presentation modalities such as text, image, audio, and video. Recent developments in multimodal machine learning now make it possible to capture basic “descriptive” relations between modalities–such as correspondences between words and phrases, on the one hand, and corresponding visual depictions of the verbally expressed information on the other. Although such advances have enabled tremendous progress in tasks like image captioning, text-to-image generation and visual question answering, in domains such as news dissemination, there is a need to go further. In this paper, we introduce a novel framework for the computational analysis of multimodal news. We motivate a set of more complex image-text relations as well as multimodal news values based on real examples of news reports and consider their realization by computational approaches. To this end, we provide (a) an overview of existing literature from semiotics where detailed proposals have been made for taxonomies covering diverse image-text relations generalisable to any domain; (b) an overview of computational work that derives models of image-text relations from data; and (c) an overview of a particular class of news-centric attributes developed in journalism studies called news values. The result is a novel framework for multimodal news analysis that closes existing gaps in previous work while maintaining and combining the strengths of those accounts. We assess and discuss the elements of the framework with real-world examples and use cases, setting out research directions at the intersection of multimodal learning, multimodal analytics and computational social sciences that can benefit from our approach.

A fruitful approach towards neuromorphic computing is to mimic mechanisms of the brain in physical devices, which has led to successful replication of neuronlike dynamics and learning in the past. However, there remains a large set of neural self-organization mechanisms whose role for neuromorphic computing has yet to be explored. One such mechanism is homeostatic plasticity, which has recently been proposed to play a key role in shaping network dynamics and correlations. Here, we study—from a statistical-physics point of view—the emergent collective dynamics in a homeostatically regulated neuromorphic device that emulates a network of excitatory and inhibitory leaky integrate-and-fire neurons. Importantly, homeostatic plasticity is only active during the training stage and results in a heterogeneous weight distribution that we fix during the analysis stage. We verify the theoretical prediction that reducing the external input in a homeostatically regulated neural network increases temporal correlations, measuring autocorrelation times exceeding 500ms, despite single-neuron timescales of only 20ms, both in experiments on neuromorphic hardware and in computer simulations. However, unlike theoretically predicted near-critical fluctuations, we find that temporal correlations can originate from an emergent bistability. We identify this bistability as a fluctuation-induced stochastic switching between metastable active and quiescent states in the vicinity of a nonequilibrium phase transition. Our results thereby constitute a complementary mechanism for emergent autocorrelations in networks of spiking neurons with implications for future developments in neuromorphic computing.

Neuromorphic systems open up opportunities to enlarge the explorative space for computational research. However, it is often challenging to unite efficiency and usability. This work presents the software aspects of this endeavor for the BrainScaleS-2 system, a hybrid accelerated neuromorphic hardware architecture based on physical modeling. We introduce key aspects of the BrainScaleS-2 Operating System: experiment workflow, API layering, software design, and platform operation. We present use cases to discuss and derive requirements for the software and showcase the implementation. The focus lies on novel system and software features such as multi-compartmental neurons, fast re-configuration for hardware-in-the-loop training, applications for the embedded processors, the non-spiking operation mode, interactive platform access, and sustainable hardware/software co-development. Finally, we discuss further developments in terms of hardware scale-up, system usability, and efficiency.

Since the beginning of information processing by electronic components, the nervous system has served as a metaphor for the organization of computational primitives. Brain-inspired computing today encompasses a class of approaches ranging from using novel nano-devices for computation to research into large-scale neuromorphic architectures, such as TrueNorth, SpiNNaker, BrainScaleS, Tianjic, and Loihi. While implementation details differ, spiking neural networks—sometimes referred to as the third generation of neural networks—are the common abstraction used to model computation with such systems. Here we describe the second generation of the BrainScaleS neuromorphic architecture, emphasizing applications enabled by this architecture. It combines a custom analog accelerator core supporting the accelerated physical emulation of bio-inspired spiking neural network primitives with a tightly coupled digital processor and a digital event-routing network.

The BrainScaleS-2 (BSS-2) system implements physical models of neurons as well as synapses and aims for an energy-efficient and fast emulation of biological neurons. When replicating neuroscientific experiments on BSS-2, a major challenge is finding suitable model parameters. This study investigates the suitability of the sequential neural posterior estimation (SNPE) algorithm for parameterizing a multi-compartmental neuron model emulated on the BSS-2 analog neuromorphic system. The SNPE algorithm belongs to the class of simulation-based inference methods and estimates the posterior distribution of the model parameters; access to the posterior allows quantifying the confidence in parameter estimations and unveiling correlation between model parameters. For our multi-compartmental model, we show that the approximated posterior agrees with experimental observations and that the identified correlation between parameters fits theoretical expectations. Furthermore, as already shown for software simulations, the algorithm can deal with high-dimensional observations and parameter spaces when the data is generated by emulations on BSS-2. These results suggest that the SNPE algorithm is a promising approach for automating the parameterization and the analyzation of complex models, especially when dealing with characteristic properties of analog neuromorphic substrates, such as trial-to-trial variations or limited parameter ranges.

The first-generation of BrainScaleS, also referred to as BrainScaleS-1, is a neuromorphic system for emulating large-scale networks of spiking neurons. Following a ‘physical modeling’ principle, its VLSI circuits are designed to emulate the dynamics of biological examples: analog circuits implement neurons and synapses with time constants that arise from their electronic components’ intrinsic properties. It operates in continuous time, with dynamics typically matching an acceleration factor of 10 000 compared to the biological regime. A fault-tolerant design allows it to achieve wafer-scale integration despite unavoidable analog variability and component failures. In this paper, we present the commissioning process of a BrainScaleS-1 wafer module, providing a short description of the system’s physical components, illustrating the steps taken during its assembly and the measures taken to operate it. Furthermore, we reflect on the system’s development process and the lessons learned to conclude with a demonstration of its functionality by emulating a wafer-scale synchronous firing chain, the largest spiking network emulation ran with analog components and individual synapses to date.

We present the BrainScaleS-2 mobile system as a compact analog inference engine based on the BrainScaleS-2 ASIC and demonstrate its capabilities at classifying a medical electrocardiogram dataset. The analog network core of the ASIC is utilized to perform the multiply-accumulate operations of a convolutional deep neural network. At a system power consumption of 5.6W, we measure a total energy consumption of $\mathrm {192 ~\mu \text {J} }$ for the ASIC and achieve a classification time of 276 $\mu$ s per electrocardiographic patient sample. Patients with atrial fibrillation are correctly identified with a detection rate of (93.7 ± 0.7)% at (14.0 ± 1.0)% false positives. The system is directly applicable to edge inference applications due to its small size, power envelope, and flexible I/O capabilities. It has enabled the BrainScaleS-2 ASIC to be operated reliably outside a specialized lab setting. In future applications, the system allows for a combination of conventional machine learning layers with online learning in spiking neural networks on a single neuromorphic platform.

Abstract Background Advanced Trauma Life Support (ATLS) is the gold standard of initial assessment of trauma patients and therefore a widely used training program for medical professionals. Practical application of the knowledge taught can be challenging for medical students and inexperienced clinicians. Simulation-based training, including virtual reality (VR), has proven to be a valuable adjunct to real-world experiences in trauma education. Previous studies have demonstrated the effectiveness of VR simulations for surgical and technical skills training. However, there is limited evidence on VR simulation training specifically for trauma education, particularly within the ATLS curriculum. The purpose of this pilot study is to evaluate the feasibility, effectiveness, and acceptance of using a fully immersive VR trauma simulation to prepare medical students for the ATLS course. Methods This was a prospective randomised controlled pilot study on a convenience sample of advanced medical students (n = 56; intervention group with adjunct training using a commercially available semi-automated trauma VR simulation, n = 28, vs control group, n = 28) taking part in the ATLS course of the Military Physician Officer School. Feasibility was assessed by evaluating factors related to technical factors of the VR training (e.g. rate of interruptions and premature termination). Objective and subjective effectiveness was assessed using confidence ratings at four pre-specified points in the curriculum, validated surveys, clinical scenario scores, multiple choice knowledge tests, and ATLS final clinical scenario and course pass rates. Acceptance was measured using validated instruments to assess variables of media use (Technology acceptance, usability, presence and immersion, workload, and user satisfaction). Results The feasibility assessment demonstrated that only one premature termination occurred and that all remaining participants in the intervention group correctly stabilised the patient. No significant differences between the two groups in terms of objective effectiveness were observed (p = 0.832 and p = 0.237 for the pretest and final knowledge test, respectively; p = 0.485 for the pass rates for the final clinical scenario on the first attempt; all participants passed the ATLS course). In terms of subjective effectiveness, the authors found significantly improved confidence post-VR intervention (p