Results 91 to 100 of about 44,639 (273)

VAE+DDPG: An Attention‐Enhanced Variational Autoencoder for Deep Reinforcement Learning‐Based Autonomous Navigation in Low‐Light Environments

Advanced Intelligent Systems, EarlyView.
Variational Autoencoder+Deep Deterministic Policy Gradient addresses low‐light failures of infrared depth sensing for indoor robot navigation. Stage 1 pretrains an attention‐enhanced Variational Autoencoder (Convolutional Block Attention Module+Feature Pyramid Network) to map dark depth frames to a well‐lit reconstruction, yielding a 128‐D latent code ...
Uiseok Lee, Chanhong Hwang, Hyunseok Kang, Yechan Park, Hangwoo Jin, Tuan Anh Nguyen, Eunmi Choi, Dugki Min   +7 more
wiley   +1 more source

Hölder regularity of the SLE trace [PDF]

Transactions of the American Mathematical Society, 2008
Summary: \textit{S. Rohde} and \textit{O. Schramm} have recently shown that the SLE trace is Hölder continuous [Ann. Math. (2) 161, No.~2, 883--924 (2005; Zbl 1081.60069)]. However, their results are not optimal for all values of \( \kappa\) and only yield a Hölder exponent near \( \frac{1}{2}\) for \( \kappa\) near 0.
openaire   +1 more source

Scalable Platform Enabling Reservoir Computing With Nanoporous Oxide Memristors for Image Recognition and Time Series Prediction

Advanced Intelligent Systems, EarlyView.
The approach of physical in materia computing incorporates parallel computing within the medium itself. A scalable and energy‐efficient, oxide‐based computational platform is realized in form of a nanoporous network of volatile niobium oxide memristors sandwiched between top and bottom metallic electrodes, and then tested for prediction and ...
Joshua Donald, Ben A. Johnson, Amir Mehrnejat, Alex Gabbitas, Arthur G. T. Coveney, Alexander G. Balanov, Sergey Savel’ev, Pavel Borisov   +7 more
wiley   +1 more source

Optimizing 3D Bin Packing of Heterogeneous Objects Using Continuous Transformations in SE(3)

Advanced Intelligent Systems, EarlyView.
This article presents a method for solving the three‐dimensional bin packing problem for heterogeneous objects using continuous rigid‐body transformations in SE(3). A heuristic optimization framework combines signed‐distance functions, neural network approximations, point‐cloud bin modeling, and physics simulation to ensure feasibility and stability ...
Michele Angelini, Marco Carricato
wiley   +1 more source

Regularized trace of the Sturm-Liouville operator with irregular boundary conditions

Electronic Journal of Differential Equations, 2009
We consider the spectral problem for the Sturm-Liouville equation with a complex-valued potential $q(x)$ and with irregular boundary conditions on the interval $(0,pi)$. We establish a formula for the first regularized trace of the this operator.
doaj  

Cohomology of classes of symbols and classi cation of traces on corresponding classes of operators with non positive order

, 2010
This thesis is devoted to the classification issue of traces on classical pseudo-differential operators with fixed non positive order on closed manifolds of dimension $n>1$.
Neira Jiménez, C.
core  

MusicSwarm: Biologically Inspired Intelligence for Music Composition

Advanced Intelligent Systems, EarlyView.
Biologically inspired swarms of frozen foundation models self‐organize to compose complex music without fine‐tuning. By coordinating through stigmergic signals, decentralized agents dynamically evolve specialized roles and adapt to solve complex tasks.
Markus J. Buehler
wiley   +1 more source

Pseudodifferential Operators and Regularized Traces

, 2009
This paper is based on talks delivered in summer 2008 at the Conference on Motives, QFT and Pseudodifferential Operators in Boston, and at the Trimester programme Geometry and Physics, Hausdorff Institute for Mathematics in Bonn The paper surveys the pseudodifferential calculus with parameter, resolvent expansions, Dixmier trace, noncommutative residue,
openaire   +2 more sources

Controlling Dynamical Systems Into Unseen Target States Using Machine Learning

Advanced Intelligent Systems, EarlyView.
Parameter‐aware next‐generation reservoir computing enables efficient, data‐driven control of dynamical systems across unseen target states and nonstationary transitions. The approach suppresses transient behavior while navigating system collapse scenarios with minimal training data—over an order of magnitude less than traditional methods.
Daniel Köglmayr, Alexander Haluszczynski, Christoph Räth   +2 more
wiley   +1 more source

Fairness-Aware Optimization in Spatio-Temporal Epidemic Data Mining: A Graph-Augmented Temporal Fusion Transformer

Mathematics
Modeling the complex spatio-temporal dynamics of infectious diseases presents a significant computational challenge due to heterogeneous regional interactions, high-dimensional multimodal data streams, and the critical need for algorithmic fairness. This
Saleh Albahli
doaj   +1 more source