SNRA combines power-efficient probabilistic and deterministic computing for deep belief networks.
problem Efficiently training and evaluating deep belief networks with low power consumption.
method Developed a spintronic neuromorphic reconfigurable array (SNRA) for in-circuit training and evaluation of deep belief networks (DBNs). Used probabilistic spin logic devices and a four-state finite state machine for unsupervised training.
result SNRA achieves more than 80% reduction in combined dynamic and static power dissipation compared to SRAM-based configurable fabrics.
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.
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.
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…
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…
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.
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.
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.
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.
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.
Improves magnetic field mapping using an array of magnetometers with noisy input.
problem Improving magnetic field maps in indoor environments with noisy magnetometer data.
method Uses Gaussian process regression with an array of magnetometers, incorporating known array positions and relative magnetometer locations.
result The method produces higher quality magnetic field maps compared to using a single magnetometer.
Simpler proof for non-basic sets in 2D.
problem Proving non-basic sets in 2D.
method Defining Sternfeld arrays and proving non-basic sets.
result Simpler proof of non-basic sets in 2D.
Paper improves DOA estimation in sparse arrays using Siamese neural networks.
problem Challenges in DOA estimation with limited snapshots in sparse linear arrays.
method Introduces a Siamese neural network with a sparse augmentation layer for enhanced signal feature embedding.
result Demonstrates improved DOA estimation accuracy in sparse arrays.
Direction of arrival (DoA) estimation of targets improves with the number of elements employed by a phased array radar antenna. Since larger arrays have high associated cost, area and computational load, there is recent interest in thinning the antenna arrays without loss of far-field DoA accuracy. In this context, a c…
QFlow learns to prioritize video streaming to improve quality of experience.
problem Inconsistent video streaming quality due to network inefficiency.
method Develops a learning approach to dynamically allocate resources for video streaming.
result Demonstrates improved video quality for all clients at a wireless access point.
Analog arrays are a promising upcoming hardware technology with the potential to drastically speed up deep learning. Their main advantage is that they compute matrix-vector products in constant time, irrespective of the size of the matrix. However, early convolution layers in ConvNets map very unfavorably onto analog a…
Novel CNN array for sign language recognition using wearable IMUs.
problem Efficiently recognizing sign language from wearable IMU signals.
method Two-dimensional Convolutional Neural Network array architecture for Indian sign language recognition.
result Peak classification accuracies of 94.20% for general sentences and 95.00% for interrogative sentences achieved.
The CHAMPION study clusters multi-dimensional accelerometer data to understand health links.
problem Clustering multi-dimensional data from pediatric longitudinal studies.
method Developed a finite mixture of multidimensional arrays model for clustering 4-dimensional accelerometer data.
result Demonstrated the feasibility and utility of clustering higher order data.
Massive MIMO is a variant of multiuser MIMO where the number of base-station antennas M is very large (typically 100), and generally much larger than the number of spatially multiplexed data streams (typically 10). Unfortunately, the front-end A/D conversion necessary to drive hundreds of antennas, with a signal band…
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 algorithm eliminates symmetry requirement for training neural networks on resistive device arrays.
problem Training accuracy on resistive device arrays depends on device switching symmetry.
method Developed 'Tiki-Taka' algorithm to minimize unintentional cost term due to device asymmetry.
result Achieves same accuracy with non-symmetric devices as with symmetric devices.
This paper improves neural network efficiency by combining filter columns and retraining, boosting array utilization and accuracy.
problem Efficient implementation of sparse convolutional neural networks on systolic arrays.
method Column combining of filter matrices, retraining of remaining weights, joint optimization for high utilization and accuracy.
result Significantly increased systolic array utilization efficiency (e.g., ~4x) and maintained high classification accuracy.
Missing data is an important challenge when dealing with high dimensional data arranged in the form of an array. In this paper, we propose methods for estimation of the parameters of array variate normal probability model from partially observed multiway data. The methods developed here are useful for missing data impu…
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.
A neural network, IHT-Net, improves DOA estimation with sparse arrays.
problem Single-snapshot DOA estimation with sparse arrays in dynamic settings.
method IHT-inspired neural network with recurrent neural network and autoencoders.
result IHT-Net achieves faster convergence and higher accuracy in DOA estimation.
Myia compiler optimizes ML models with efficient AD for array programming.
problem Efficient automatic differentiation for array programming in ML.
method Introduces a new graph-based IR that supports function calls, higher-order functions, and recursion.
result Myia compiler enables efficient AD using source transformation without a tape, supporting higher-order derivatives.
Efficient non-uniform quantizer improves CNN performance on FPGA.
problem Improving CNN performance on low-power systems like mobile devices.
method Custom hardware-friendly non-uniform quantizer for parameters and activations using a single scale integer representation.
result Little degradation in accuracy on CIFAR-10 and CIFAR-100 datasets.
Robust STAP with coprime arrays reduces clutter using sparse modeling.
problem Limited performance due to training samples support in practical applications.
method Two-stage approach: 1) RD virtual snapshot, 2) RD sparse measurement modeling with OMP-like recovery.
result Robust to prior knowledge errors, good clutter suppression performance.
Paper proposes a learning-based sparse Bayesian method for accurate off-grid DOA estimation.
problem One-bit off-grid direction of arrival (DOA) estimation in a single snapshot scenario.
method Formulated off-grid DOA estimation model, used Sparse Bayesian framework, proposed Learning-based Sparse Bayesian approach.
result Improved computational efficiency and accuracy in off-grid DOA estimation.
Infinite Tucker Decomposition (InfTucker) and random function prior models, as nonparametric Bayesian models on infinite exchangeable arrays, are more powerful models than widely-used multilinear factorization methods including Tucker and PARAFAC decomposition, (partly) due to their capability of modeling nonlinear rel…
We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and global optimizations such as loop transformations. Thanks to this feature, we demo…
We augment the nonnegative matrix factorization method for audio source separation with cues about directionality of sound propagation. This improves separation quality greatly and removes the need for training data, with only a twofold increase in run time. This is the first method which can exploit directional inform…
NLM combines neural networks and logic programming for complex reasoning.
problem Complex reasoning tasks involving logic and properties.
method Neural-symbolic architecture combining neural networks and logic programming.
result NLM achieves perfect generalization on various tasks.
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.
Anomaly detection is one of the frequent and important subroutines deployed in large-scale data processing systems. Even being a well-studied topic, existing techniques for unsupervised anomaly detection require storing significant amounts of data, which is prohibitive from memory and latency perspective. In the big-da…
Deep neural networks improve angle of arrival estimation with lower complexity.
problem Estimating the number of sources and their angles of arrival from a single antenna array observation.
method Apply a deep neural network (DNN) approach to the problem.
result Deep neural networks can attain maximum likelihood performance with feasible complexity and outperform other methods.
This paper proposes a learning framework for n-bit quantized neural networks that improves accuracy and speed on FPGAs.
problem Efficiently implementing quantized neural networks on FPGAs to maintain accuracy and speed.
method A novel learning framework for n-bit QNNs, constrained weights, reconstructed gradient function, n-BQ-NN structure, and SVPE array.
result Quantized models achieve almost the same accuracy as full-precision models and outperform typical low-precision QNNs.
We consider two eigenvalue problems for Laplacian on some specific doubly connected domain. In particular, we study the following two eigenvalue problems. Let B1 be an open ball in Rn and B0 be a ball contained in B1. Let ν be the outward unit normal on ∂B1. Then the first eigenvalue o…