Zobrazeno 1 - 10
of 2 264
pro vyhledávání: '"Niskanen, P"'
Encoder--decoder neural networks (EDNN) condense information most relevant to the output of the feedforward network to activation values at a bottleneck layer. We study the use of this architecture in emulation and interpretation of simulated X-ray s
Externí odkaz:
http://arxiv.org/abs/2406.14044
Structural Descriptors and Information Extraction from X-ray Emission Spectra: Aqueous Sulfuric Acid
Machine learning can reveal new insights into X-ray spectroscopy of liquids when the local atomistic environment is presented to the model in a suitable way. Many unique structural descriptor families have been developed for this purpose. We benchmar
Externí odkaz:
http://arxiv.org/abs/2402.08355
A major challenge in inductive logic programming is learning big rules. To address this challenge, we introduce an approach where we join small rules to learn big rules. We implement our approach in a constraint-driven system and use constraint solve
Externí odkaz:
http://arxiv.org/abs/2401.16215
We present a PyTorch-powered implementation of the emulator-based component analysis used for ill-posed numerical non-linear inverse problems, where an approximate emulator for the forward problem is known. This emulator may be a numerical model, an
Externí odkaz:
http://arxiv.org/abs/2312.12967
Autor:
Sanni Peltonen, Tuuli-Maria Sonninen, Jonna Niskanen, Jari Koistinaho, Marika Ruponen, Šárka Lehtonen
Publikováno v:
Fluids and Barriers of the CNS, Vol 21, Iss 1, Pp 1-12 (2024)
Abstract Background Pericytes play a crucial role in controlling inflammation and vascular functions in the central nervous system, which are disrupted in Parkinson’s disease (PD). Still, there is a lack of studies on the impact of pericytes on neu
Externí odkaz:
https://doaj.org/article/40491bcb47914518b2652d7ebe326de0
Many inductive logic programming approaches struggle to learn programs from noisy data. To overcome this limitation, we introduce an approach that learns minimal description length programs from noisy data, including recursive programs. Our experimen
Externí odkaz:
http://arxiv.org/abs/2308.09393
We study the Identity Problem, the problem of determining if a finitely generated semigroup of matrices contains the identity matrix; see Problem 3 (Chapter 10.3) in ``Unsolved Problems in Mathematical Systems and Control Theory'' by Blondel and Megr
Externí odkaz:
http://arxiv.org/abs/2307.05283
Publikováno v:
Journal of Physics Communications 8 (2024) 025001
We apply a recently developed technique utilizing machine learning for statistical analysis of computational nitrogen K-edge spectra of aqueous triglycine. This method, the emulator-based component analysis, identifies spectrally relevant structural
Externí odkaz:
http://arxiv.org/abs/2306.08512
Autor:
Niskanen, J. A.
Publikováno v:
European Physical Journal A, 60 5 (2024) 109
It is known that at their threshold intermediate two-baryon NDelta states can produce resonance-like structures in some isospin one states, often interpreted as more exotic manifest six-quark states. This paper applies the coupled-channel method to s
Externí odkaz:
http://arxiv.org/abs/2305.08647
Artificial intelligence is more ubiquitous in multiple domains. Smartphones, social media platforms, search engines, and autonomous vehicles are just a few examples of applications that utilize artificial intelligence technologies to enhance their pe
Externí odkaz:
http://arxiv.org/abs/2305.04532