Related papers: The VO-Neural project: recent developments and som…

Variable Star Network (VSNET, http://www.kusastro.kyoto-u.ac.jp/vsnet/) is a global professional-amateur network of researchers in variable stars and related objects, particularly in transient objects, such as cataclysmic variables, black…

Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse datasets has thus far hampered a direct intercomparison of different approaches. Here…

Neural operators (NOs) are designed to learn maps between infinite-dimensional function spaces. We propose a novel reframing of their use. By introducing an auxiliary base-space, any finite-dimensional function can be viewed as an operator…

With the improvement of computer performance and the increase of data volume, the object detection based on convolutional neural network (CNN) has become the main algorithm for object detection. This paper summarizes the research progress…

This paper introduces a novel approach in neuromorphic computing, integrating heterogeneous hardware nodes into a unified, massively parallel architecture. Our system transcends traditional single-node constraints, harnessing the neural…

Object Goal Navigation (ObjectNav) refers to an agent navigating to an object in an unseen environment, which is an ability often required in the accomplishment of complex tasks. While existing methods demonstrate proficiency in isolated…

The combination of traditional rendering with neural networks in Deferred Neural Rendering (DNR) provides a compelling balance between computational complexity and realism of the resulting images. Using skinned meshes for rendering…

The U.S. Virtual Astronomical Observatory (VAO) is a product-driven organization that provides new scientific research capabilities to the astronomical community. Software development for the VAO follows a lightweight framework that guides…

Neural Operators (NOs) are a leading method for surrogate modeling of partial differential equations. Unlike traditional neural networks, which approximate individual functions, NOs learn the mappings between function spaces. While NOs have…

The European Virtual Observatory (VO) initiative organises regular VO schools since 2008. The goals are twofold: i) to expose early-career European astronomers to the variety of currently available VO tools and services so that they can use…

Neural networks as well as other methods of machine learning (ML) are known to be highly efficient in different classification tasks, including classification of images and videos. Mini- EUSO is a wide-field-of-view imaging telescope that…

Applied research in graph algorithms and combinatorial structures needs comprehensive and versatile software libraries. However, the design and the implementation of flexible libraries are challenging activities. Among the other problems…

We propose a proof of concept for a variational distributional neuron: a compute unit formulated as a VAE brick, explicitly carrying a prior, an amortized posterior and a local ELBO. The unit is no longer a deterministic scalar but a…

Machine-learning is playing an increasing role in helping the astronomical community to face data analysis challenges, in particular in the field of Galactic Archaeology and large scale spectroscopic surveys. We present recent developments…

This article presents a newly developed Web portal called VisIVOWeb that aims to provide the astrophysical community with powerful visualization tools for large-scale data sets in the context of Web 2.0. VisIVOWeb can effectively handle…

The Artificial Neural network is a functional imitation of simplified model of the biological neurons and their goal is to construct useful computers for real world problems. The ANN applications have increased dramatically in the last few…

Despite the lack of important functions supported only by legacy applications, the current VO-compatible tools have enough capabilities to allow powerful analysis of stellar spectra using both public archives and local proprietary data. We…

A novel Neural Network architecture is proposed using the mathematically and physically rich idea of vector fields as hidden layers to perform nonlinear transformations in the data. The data points are interpreted as particles moving along…

Deep Learning, driven by neural networks, has led to groundbreaking advancements in Artificial Intelligence by enabling systems to learn and adapt like the human brain. These models have achieved remarkable results, particularly in…

This work aims to assess the state of the art of data parallel deep neural network training, trying to identify potential research tracks to be exploited for performance improvement. Beside, it presents a design for a practical C++ library…