Related papers: A Space-Efficient Method for Navigable Ensemble An…
We present the first neural network that has learned to compactly represent and can efficiently reconstruct the statistical dependencies between the values of physical variables at different spatial locations in large 3D simulation…
Ensemble learning is a method of combining multiple trained models to improve model accuracy. We propose the usage of such methods, specifically ensemble average, inside Convolutional Neural Network (CNN) architectures by replacing the…
Dataflow scheduling decisions are of vital importance to neural network (NN) accelerators. Recent scalable NN accelerators support a rich set of advanced dataflow techniques. The problems of comprehensively representing and quickly finding…
Recent years have seen the paradigm shift of Named Entity Recognition (NER) systems from sequence labeling to span prediction. Despite its preliminary effectiveness, the span prediction model's architectural bias has not been fully…
Ensemble datasets are ever more prevalent in various scientific domains. In climate science, ensemble datasets are used to capture variability in projections under plausible future conditions including greenhouse and aerosol emissions. Each…
We present a new method to visualize data ensembles by constructing structured probabilistic representations in latent spaces, i.e., lower-dimensional representations of spatial data features. Our approach transforms the spatial features of…
Numerical simulations are commonly used to understand the parameter dependence of given spatio-temporal phenomena. Sampling a multi-dimensional parameter space and running the respective simulations leads to an ensemble of a large number of…
Many visual analytics systems allow users to interact with machine learning models towards the goals of data exploration and insight generation on a given dataset. However, in some situations, insights may be less important than the…
Neuroimaging open-data initiatives have led to increased availability of large scientific datasets. While these datasets are shifting the processing bottleneck from compute-intensive to data-intensive, current standardized analysis tools…
Neuronal network models and corresponding computer simulations are invaluable tools to aid the interpretation of the relationship between neuron properties, connectivity and measured activity in cortical tissue. Spatiotemporal patterns of…
The use of ensembles of neural networks (NNs) for the quantification of predictive uncertainty is widespread. However, the current justification is intuitive rather than analytical. This work proposes one minor modification to the normal…
Contemporary tasks of complex system simulation are often related to the issue of uncertainty management. It comes from the lack of information or knowledge about the simulated system as well as from restrictions of the model set being…
Recent advances in both theory and methods have created opportunities to simulate biomolecular processes more efficiently using adaptive ensemble simulations. Ensemble-based simulations are used widely to compute a number of individual…
Visual exploration of high-dimensional real-valued datasets is a fundamental task in exploratory data analysis (EDA). Existing methods use predefined criteria to choose the representation of data. There is a lack of methods that (i) elicit…
Optimizing the performance of large-scale parallel codes is critical for efficient utilization of computing resources. Code developers often explore various execution parameters, such as hardware configurations, system software choices, and…
Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…
Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently, partially…
Finite Element Analysis (FEA) is a powerful but computationally intensive method for simulating physical phenomena. Recent advancements in machine learning have led to surrogate models capable of accelerating FEA. Yet there are still…
In the past few years, augmented reality (AR) and virtual reality (VR) technologies have experienced terrific improvements in both accessibility and hardware capabilities, encouraging the application of these devices across various domains.…
In industries such as healthcare, finance, and manufacturing, analysis of unstructured textual data presents significant challenges for analysis and decision making. Uncovering patterns within large-scale corpora and understanding their…