Machine learning speeds up RIS design for efficient RF components.
problem Designing reconfigurable intelligent surfaces (RIS) for efficient RF components is time-consuming and resource-intensive.
method Machine/deep learning techniques are used to reduce the computational cost and time of RIS inverse design.
result Machine learning techniques significantly reduce the time and computational cost of RIS design.
Efficient DL reduces EM nanostructure design complexity.
problem Designing and optimizing electromagnetic nanostructures efficiently.
method Autoencoder-based dimensionality reduction for one-to-one problem reformulation.
result Significant reduction in computational complexity for EM nanostructures.
New framework aligns latent representations over-the-air using intelligent metasurfaces.
problem Heterogeneous transmitter-receiver models produce misaligned latent representations in semantic communication.
method Intelligent metasurfaces (SIM) emulate supervised and zero-shot semantic aligners directly in the wave domain.
result SIMs achieve up to 90% task accuracy in high SNR regimes, robust to low SNR.
Study improves chiral photonic metasurface design using neural networks and genetic algorithms.
problem Optimizing chiral photonic metasurfaces for high chiral dichroism and reflectivity.
method Combines neural network and genetic algorithm approaches with improved fitness functions and data augmentation.
result Demonstrates a significant increase in chiral dichroism and reflectivity.
We study rerouting edges on surfaces without crossings.
problem Reconfiguring edge paths on surfaces without crossing.
method Rerouting one edge at a time, maintaining crossing-free intermediate embeddings.
result Reconfiguration is always possible on the torus and any orientable surface of genus at least one.
A learning algorithm optimizes beamforming for holographic transceivers in far-field communication.
problem Optimal phase-shifts for beamforming in holographic transceivers are challenging due to unknown receiver locations and large phase-shifts.
method Developed a learning algorithm using a fixed-budget multi-armed bandit framework to learn optimal phase-shifts.
result The algorithm, HoloBeam, outperforms state-of-the-art methods in beamforming optimization.
Shear moves connect square-tiled surfaces in quadratic differentials.
problem Connecting square-tiled surfaces via specific moves.
method Shear moves corresponding to diagonal flips preserving square-tiled properties.
result Connected components of reconfiguration problem are in bijection with moduli space of quadratic differentials.
GraPhyR uses GNNs to optimize power grid reconfiguration in real-time.
problem Optimizing power grid reconfiguration for reliability and efficiency.
method Physics-informed Graph Neural Network (GNN) framework.
result GraPhyR learns to optimize DyR tasks efficiently.
LostGANs generate realistic images from reconfigurable layouts and styles.
problem Learning generative models for realistic images from reconfigurable layouts and styles.
method End-to-end training of GANs with two new components: mask maps and ISLA-Norm.
result State-of-the-art performance on COCO-Stuff and Visual Genome datasets.
New puzzles from geometry and topology.
problem Exploring puzzles from geometric and topological concepts.
method Construction from square-tiled shapes, discussion of underlying mathematics.
result Puzzles naturally associated to puzzle spaces.
Framework predicts and prepares for rain-induced microwave link attenuation.
problem Severe signal attenuation due to weather conditions degrades network performance.
method Predictive Network Reconfiguration (PNR) framework using LSTM for attenuation prediction and MSNR for dynamic routing.
result Framework improves network utilization by more than 200% compared to reactive algorithms.
Federated edge learning improves with CSIT-free model aggregation using RIS.
problem Lack of CSIT in federated edge learning systems.
method Use RIS to align channel coefficients for model aggregation without CSIT, optimize RIS and receiver jointly.
result Achieves similar learning accuracy as CSIT-based methods without CSIT.
Proposes AtCoR for predicting bike station usage, improving station network reconfiguration.
problem Challenges in predicting new bike stations due to lack of historical data.
method AtCoR algorithm that predicts both existing and new bike stations using station-centered heatmaps and historical correlations.
result AtCoR outperforms existing models in predicting bike station usage.
We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample…
A machine-learning method speeds up RIS design by predicting reflection coefficients.
problem Extensive full-wave EM simulations are time-consuming for RIS design.
method Combining MLP and dual-port network to develop a fast model.
result The proposed method significantly reduces the time for RIS design.
PruneTrain speeds up neural network training by dynamically pruning weights.
problem Efficiently training large neural networks with high compute and memory costs.
method Structured group-lasso regularization and reconfiguration techniques to reduce weights and model size.
result Achieved 39% reduction in end-to-end training time for ResNet50 on ImageNet.
Adversarial perturbations and RIS interaction vectors improve covert communication.
problem Covert communication in the presence of RISs.
method Designing RIS interaction vectors to balance receiver and eavesdropper detection, adding adversarial perturbations to signals.
result Adversarial perturbations and RIS interaction vectors can be jointly designed to boost covert communications.
Efficiently generates high-resolution images with reduced sampling time using LEGO bricks.
problem Efficiently generating high-resolution images with reduced sampling time.
method Introduces LEGO bricks that integrate Local-feature Enrichment and Global-content Orchestration to create a test-time reconfigurable diffusion backbone.
result Significantly reduces sampling time compared to other methods.
In this work, we give some new characterizations for inclined curves and slant helices in n-dimensional Euclidean space E^{n}. Morever, we consider the pre-characterizations about inclined curves and slant helices and reconfigure them.
In this paper, a spintronic neuromorphic reconfigurable Array (SNRA) is developed to fuse together power-efficient probabilistic and in-field programmable deterministic computing during both training and evaluation phases of restricted Boltzmann machines (RBMs). First, probabilistic spin logic devices are used to devel…
The predominant use of wireless access networks is for media streaming applications, which are only gaining popularity as ever more devices become available for this purpose. However, current access networks treat all packets identically, and lack the agility to determine which clients are most in need of service at a …
For power grid operations, a large body of research focuses on using generation redispatching, load shedding or demand side management flexibilities. However, a less costly and potentially more flexible option would be grid topology reconfiguration, as already partially exploited by Coreso (European RSC) and RTE (Frenc…
We reconfigure the Milnor invariant of links in terms of central group extensions and unipotent Magnus embeddings. We also develop a diagrammatic computation of the invariant and compute the first non-vanishing invariants of the Milnor link and of several other links. Moreover, we refine the original Milnor invariants …
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.
New method learns quantum states using neural networks, revealing hidden dynamics.
problem High-precision ground state estimation of quantum many-body problems.
method Stochastic reconfiguration method with neural network Ansatz states.
result Learning landscape modes with least entanglement have largest eigenvalues, suggesting correlations are encoded in large flat valleys.
New origami structures adapt to over 100 shapes with minimal actuation.
problem Limited shape-morphing capabilities in metamaterials and robotics.
method Hierarchical origami based on polyhedrons, using simple actuation.
result Single structure adapts to over 103 configurations with few actuations.
Designs chiral photonic structures using machine learning for efficient optical properties.
problem Optimizing chiral photonic nanostructures for light-matter interactions.
method Evolutionary algorithm and neural network approach for rapid optimization.
result Frequency-dependent modification in reflected light's degree of circular polarization.
Tying knots and linking microscopic loops of polymers, macromolecules, or defect lines in complex materials is a challenging task for material scientists. We demonstrate the knotting of microscopic topological defect lines in chiral nematic liquid crystal colloids into knots and links of arbitrary complexity by using l…
Study improves communication efficiency in RIS-assisted downlink communication.
problem Improving performance of RIS-aided downlink communication over heterogeneous designs.
method Distributed learning with distributionally robust optimization.
result Our algorithm achieves 50% fewer communication rounds for similar worst-case performance.
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…
Over-the-counter markets are at the center of the postcrisis global reform of the financial system. We show how the size and structure of such markets can undergo rapid and extensive changes when participants engage in portfolio compression, a post-trade netting technology. Tightly-knit and concentrated trading structu…
Grinch efficiently clusters large datasets with complex structures.
problem Large-scale hierarchical clustering with complex linkage functions.
method Rotate and graft subroutines for efficient reconfiguration.
result Grinch guarantees accurate cluster trees for consistent models.
Bio-inspired neuromorphic hardware is a research direction to approach brain's computational power and energy efficiency. Spiking neural networks (SNN) encode information as sparsely distributed spike trains and employ spike-timing-dependent plasticity (STDP) mechanism for learning. Existing hardware implementations of…
Bayesian mixture models are widely applied for unsupervised learning and exploratory data analysis. Markov chain Monte Carlo based on Gibbs sampling and split-merge moves are widely used for inference in these models. However, both methods are restricted to limited types of transitions and suffer from torpid mixing and…
UT module refines VAE latent space, improving disentanglement and interpretability.
problem Irregular latent distributions cause posterior collapse and misalignment in VAEs.
method UT module uses G-KDE clustering, GM modeling, and PIT to transform latent space into uniform distribution.
result UT module enhances disentanglement and interpretability of latent representations.
A single-vertex origami is a piece of paper with straight-line rays called creases emanating from a fold vertex placed in its interior or on its boundary. The Single-Vertex Origami Flattening problem asks whether it is always possible to reconfigure the creased paper from any configuration compatible with the metric, t…
Adversarial dropout improves RNNs' performance on sequential data tasks.
problem Improving generalization performance of RNNs for sequential data.
method Adversarial dropout technique for RNNs using intentionally generated dropout masks.
result Adversarial dropout improves RNNs' effectiveness on sequential tasks.
Soft modularization improves sample efficiency and performance in reinforcement learning.
problem Challenges in training multiple tasks jointly in reinforcement learning.
method Explicit modularization technique on policy representation, soft modularization method.
result Improves sample efficiency and performance over strong baselines in robotics manipulation tasks.
Researchers propose a non-monotone quantum natural gradient for quantum systems.
problem Applying natural gradient methods to quantum systems without monotonicity.
method Introducing a non-monotone quantum natural gradient (QNG) and demonstrating its superiority over conventional QNG.
result Non-monotone QNG outperforms conventional QNG in terms of convergence speed.
New algorithms for constrained online optimization with memory and predictions.
problem Control of constrained dynamical systems and scheduling with reconfiguration budgets.
method Proposed algorithms achieving sublinear regret and constraint violation under time-varying constraints, both with and without predictions.
result First algorithms achieving sublinear regret and constraint violation in constrained online optimization with memory.
Single neurons can perform as well as dense networks in binary and multi-class recognition tasks.
problem Designing efficient neural networks for recognition tasks.
method Investigated the use of single or multiple neurons in neural networks for binary and multi-class recognition tasks.
result Sparse networks can be as efficient as dense networks in both binary and multi-class tasks.
Adaptive algorithms minimize regret in matching markets with contextual arm preferences.
problem Minimizing regret in matching markets with context-dependent player utilities.
method Developed adaptive algorithms for stochastic and adversarial contexts, providing upper and lower bounds.
result Achieved sublinear regret bounds for both stochastic and adversarial contexts.
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural networks (DNNs). An algorithm-hardware co-optimization framework is developed, which i…
The paper characterizes brain states and transitions using functional MRI data.
problem Characterizing the dynamic reconfiguration of neural systems in brain states.
method Bayesian model-based characterization of latent brain states and posterior predictive discrepancy using the latent block model.
result The model detects transitions between latent brain states and identifies distinctive community patterns in task-fMRI data.
Deep learning simplifies nanophotonic device physics.
problem Understanding light-matter interactions in nanophotonic devices.
method Deep learning algorithm with dimensionality reduction.
result Extracts useful information about nanostructure features.
Convolutional Neural Networks (CNN) has become more popular choice for various tasks such as computer vision, speech recognition and natural language processing. Thanks to their large computational capability and throughput, GPUs ,which are not power efficient and therefore does not suit low power systems such as mobil…
In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applyin…
In order to fully utilize "big data", it is often required to use "big models". Such models tend to grow with the complexity and size of the training data, and do not make strong parametric assumptions upfront on the nature of the underlying statistical dependencies. Kernel methods fit this need well, as they constitut…