Analog arrays speed up ConvNets by parallelizing kernel matrix training.
problem Early ConvNets struggle with analog arrays due to small kernel matrices.
method Replicate kernel matrix on multiple analog arrays, training in parallel.
result Analog arrays achieve high acceleration factors (16-128) for ConvNets.
In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resistive devices for deep learning. This concept of Resistive Processing Unit (RPU) devices we extend here towards convolutional neural networks (…
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.
Improves RNN performance under noisy computations.
problem Power and speed limitations in deep learning with noisy analog circuits.
method Deep Noise Injection training to robustify RNN weights/biases.
result Trained RNNs show more consistent performance under noisy inference.
The algebras of valuations on S6 and S7 invariant under the actions of G2 and Spin(7) are shown to be isomorphic to the algebra of translation-invariant valuations on the tangent space at a point invariant under the action of the isotropy group. This is in analogy with the cases of real and …
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…
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.
One-step learning in crosspoint memory reduces computation time.
problem Real-time AI at the edge requires fast, low-energy computing.
method Crosspoint resistive memory with feedback configures linear and logistic regression.
result Linear and logistic regression can be computed in one step.
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…
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.
Study noise in inference to improve accuracy and security.
problem Noise in inference affects deep learning systems' accuracy and security.
method Noise-injected training and voting method for improving accuracy; defensive architecture for adversarial attacks.
result Significant improvement in accuracy and robustness against attacks.
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.
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.
Tangent automates derivatives in Python, improving expressiveness and performance.
problem Efficiently calculating derivatives for complex models in Python.
method Source-code transformation for dynamically typed array programming.
result Demonstrates improved expressiveness and performance in automatic differentiation.
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…
Extends denoising and score estimation to energy models via Tweedie's formula.
problem Linking denoising and score estimation for a wider range of distributions.
method Derives a fundamental identity connecting energy score derivatives and scores.
result Establishes a new identity for energy scores analogous to Tweedie's formula.
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…
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.
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…
In this paper we prove the following geometric inequality in the hyperbolic space $\H^n$ (n≥5), which is a hyperbolic Alexandrov-Fenchel inequality, \[\begin{array}{rcl} \ds \int_Σ\s_4 d μ\ge \ds\vs C_{n-1}^4ω_{n-1}\left\{\left(\frac{|Σ|}{ω_{n-1}} \right)^\frac 12 + \left(\frac{|Σ|}{ω_{n-1}} \right)^{\frac 12\frac…
The paper proves existence of solutions for mean field equations on compact Riemann surfaces.
problem Existence of solutions for mean field equations on compact Riemann surfaces.
method Min-max scheme introduced by Djadli-Malchiodi (2006) and Djadli (2008).
result Proves existence of solutions for mean field equations on compact Riemann surfaces.
Differentiable sorting framework using optimal transport.
problem Piecewise constant sorting function without gradient information.
method Linking sorting to optimal transport, adding entropic regularization, and approximating with Sinkhorn iterations.
result Differentiable sorting operators (S-sorts, S-CDFs, S-quantiles) for machine learning applications.
Techniques for data-mining, latent semantic analysis, contextual search of databases, etc. have long ago been developed by computer scientists working on information retrieval (IR). Experimental scientists, from all disciplines, having to analyse large collections of raw experimental data (astronomical, physical, biolo…
In order to cope with the increased data volumes generated by modern radio interferometers such as LOFAR (Low Frequency Array) or SKA (Square Kilometre Array), fast and efficient calibration algorithms are essential. Traditional radio interferometric calibration is performed using nonlinear optimization techniques such…
This paper introduces an efficient method for optimizing deep learning hyperparameters.
problem The high dependency of deep learning algorithms on hyper-parameters.
method Orthogonal Array Tuning Method (OATM) for deep learning hyper-parameter tuning.
result The proposed OATM method significantly saves tuning time compared to state-of-the-art methods.
This paper proves a conjecture about unique positive harmonic functions in a ball.
problem Proving the uniqueness of positive harmonic functions in a unit ball for specific parameters.
method Analyzing a partial differential equation to show the solution is constant.
result Guo-Wang's conjecture is proven for the specified parameters.
Stochastic partition models tailor a product space into a number of rectangular regions such that the data within each region exhibit certain types of homogeneity. Due to constraints of partition strategy, existing models may cause unnecessary dissections in sparse regions when fitting data in dense regions. To allevia…
We apply the OSCAR (octagonal selection and clustering algorithms for regression) in recovering group-sparse matrices (two-dimensional---2D---arrays) from compressive measurements. We propose a 2D version of OSCAR (2OSCAR) consisting of the ℓ1 norm and the pair-wise ℓ∞ norm, which is convex but non-d…
Paper solves curvature prescription problem on surfaces with boundary.
problem Prescribing Gaussian and geodesic curvatures on compact surfaces with boundary.
method Mean field-type formulation and variational techniques.
result Existence results for positive, zero, and negative Euler characteristics.
Improved classifier accuracy by using more of the class-specific structure in trained models.
problem Softmax ignores valuable information encoded in the full array of class response distributions.
method Developed a hybrid classifier (Softmax-Pooling Hybrid, SPH) that uses Softmax on high-scoring samples and a log-likelihood method on low-scoring samples. result Reduces test set error by 6% to 23% using the exact same trained model.
This paper designs sensor arrays for estimating unsteady flows efficiently.
problem Estimating high-dimensional unsteady flow fields with limited sensor placement.
method Combines data-driven modeling, Kalman Filter design, and sparsification for sensor selection.
result Proposed sensor arrays are highly effective for flow-field estimation across various conditions.
Study evaluates risk in options using volatility surface projections.
problem Risk assessment of options due to their non-linear price behavior and volatility fluctuations.
method Parametric surface projection method for implied volatility.
result Enhanced risk evaluation through dynamic volatility surface analysis.
Graph-based rehearsal improves continual learning performance.
problem Catastrophic forgetting in continual learning models.
method Augmenting a memory array with a learnable random graph to capture pairwise similarities.
result Our model consistently outperforms baselines on task-free continual learning benchmarks.
Proves existence of solutions for a specific nonlinear equation on Riemannian manifolds.
problem Existence of solutions for a doubly nonlinear evolution equation on Riemannian manifolds.
method Proves existence of weak solutions using the Leibenson equation.
result Proves the existence of a unique weak solution for any initial condition in L1(M)∩L∞(M). A neural network improves DOA estimation from a single snapshot.
problem Estimating DOAs from a single snapshot with limited aperture.
method Deep learning architecture trained to generate high-resolution spatial spectrum.
result Our (SP)2-Net outperforms classical methods. Framework for systemic risk modeling using jointly exchangeable arrays.
problem Systemic risk in insurance portfolios with interactions.
method Jointly exchangeable arrays, central limit theorems, simulation-based validation.
result Asymptotic approximations for total portfolio losses in large portfolios over long time horizons.
Let (M,g) be a n−dimensional compact Riemannian manifold with boundary. We consider the Yamabe type problem \begin{equation} \left\{ \begin{array}{ll} -Δ_{g}u+au=0 & \text{ on }M \\ \partial_νu+\frac{n-2}{2}bu= u^{{n\over n-2}\pm\varepsilon} & \text{ on }\partial M \end{array}\right. \end{equation} where $a\in C^1(…