New NN design for nonlinear systems control with guarantees.
problem Designing NN architectures for nonlinear system control with guarantees.
method Exploits system model to design NN architecture, uses TLL NN for approximation.
result Guaranteed NN architecture sufficient for implementing a controller.
Different neural network (NN) architectures have different advantages. Convolutional neural networks (CNNs) achieved enormous success in computer vision, while recurrent neural networks (RNNs) gained popularity in speech recognition. It is not known which type of NN architecture is the best fit for classification of co…
A novel neural network approach for optimization problems.
problem Constrained optimization problems.
method Neural Optimization Machine (NOM) using a specially designed NN architecture and training procedure.
result Solves optimization problems efficiently, especially in high-dimensional spaces.
uGMM-NN integrates probabilistic reasoning into neural networks.
problem Capturing multimodality and uncertainty in neural network activations.
method Parameterizes activations as univariate Gaussian mixtures with learnable parameters.
result Competitive discriminative performance with probabilistic activations.
NNs can learn efficient algorithms for certain problems.
problem Learning efficient algorithms for specific problems.
method Recurrent Convolutional Neural Networks (RCNNs) that learn efficiently.
result RCNNs can learn as well as efficient algorithms described by a constant-sized program.
Gatherings of thousands to millions of people frequently occur for an enormous variety of events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event. In this work, we show that the regularly accepted labeling scheme of crowd density maps for trai…
Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance (PFT) in their architecture; however, the biased PFT of NNs can lead to severe consequences in applications like cryptography and security …
Training a Neural Network (NN) with lots of parameters or intricate architectures creates undesired phenomena that complicate the optimization process. To address this issue we propose a first modular approach to NN design, wherein the NN is decomposed into a control module and several functional modules, implementing …
As deep neural network (NN) methods have matured, there has been increasing interest in deploying NN solutions to "edge computing" platforms such as mobile phones or embedded controllers. These platforms are often resource-constrained, especially in energy storage and power, but state-of-the-art NN architectures are de…
Study on NNs for forecasting time series with novel control variable combinations.
problem Forecast future time series with novel combinations of control variables.
method Modular NN architecture with inductive bias for independence of control variables.
result Modular NN architecture improves forecasting of dependent variables up to large horizons.
PDE-NetGen converts physical equations to neural networks for various scientific problems.
problem Bridging physics and deep learning for efficient neural network architectures.
method Combines symbolic calculus and neural network generation to translate PDEs into NN architectures.
result Generates compact, computationally-efficient physics-informed NN architectures.
The paper designs neural networks with assurance for controlling nonlinear systems.
problem Designing neural networks with assurance for nonlinear system control.
method Bounding the number of affine functions needed for a CPWA function, connecting it to a TLL NN architecture.
result The TLL NN architecture is parameterized by the number of affine functions in the CPWA function it realizes.
Paper proposes FTT-NAS to create fault-tolerant CNNs for edge devices.
problem Faults in edge devices affect deep learning applications.
method Formalized fault models, implemented FTT-NAS, incorporated FTT.
result Discovered CNNs outperform baseline architectures with fault tolerance.
Study bridges GARCH and NN models for volatility forecasting.
problem Lack of interaction between GARCH and NN approaches for volatility forecasting.
method Established equivalence between GARCH and NN models, introduced GARCH-NN approach.
result GARCH-NN approach enhances volatility forecasting compared to standalone models.
This paper uses second-order Poincaré inequalities to establish quantitative central limit theorems for Gaussian neural networks.
problem Establishing quantitative central limit theorems for Gaussian neural networks.
method Using second-order Poincaré inequalities to reduce the problem to computing the gradient and Hessian of the NN's output.
result Suboptimal rates of convergence for the NN's output due to the use of second-order Poincaré inequalities.
We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best NN architecture for a given dataset, using the NAB metric to assess the quality…
New pruning methods improve energy efficiency of neural networks.
problem Energy-efficient neural networks for devices with limited resources.
method Magnitude and Gradient based pruning at initialization and training of sparse architectures.
result Proposed novel pruning methods prevent full layer pruning and improve training.
NOMU improves neural network uncertainty estimation.
problem Estimating model uncertainty for neural networks with limited data.
method Introduces NOMU, a two-sub-NN architecture with a designed loss function.
result NOMU outperforms state-of-the-art methods in regression and Bayesian optimization.
With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems. However, despite their impressive performance on "known inputs", these NNs can fail absurdly on the "unseen inputs", especially if these real…
Attention mechanisms in deep learning become Gaussian process-like as the number of heads increases.
problem Understanding the behavior of attention mechanisms in deep learning models.
method Extending the equivalence between wide neural networks and Gaussian processes to attention architectures.
result Multi-head attention architectures behave as Gaussian processes as the number of heads tends to infinity.
Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural Networks (NNs), hardware accelerators emerge as a promising solution. However, with …
Paper proposes neural network for efficient MIMO channel estimation and pilot reduction.
problem High overhead from pilot transmission in wideband MIMO systems.
method Neural network architecture for frequency-aware pilot design and channel estimation, with pruning technique.
result Neural network outperforms linear minimum mean square error (LMMSE) estimation.
A current research trend in neurocomputing involves the design of novel artificial neural networks incorporating the concept of time into their operating model. In this paper, a novel architecture that employs stigmergy is proposed. Computational stigmergy is used to dynamically increase (or decrease) the strength of a…
New kernel connects deep learning to optimization, improving generalization.
problem Understanding why deep neural networks generalize well at over-parameterization.
method Established Neural Optimization Kernel (NOK) linking deep NN to optimization problems.
result New generalization bound for deep structured approximated NOK architecture.
Fast BATLLNN speeds up verification of TLL NNs by 400x.
problem Verifying output constraints for TLL NNs.
method Uses TLL architecture and decoupled box constraints to improve verification performance.
result 400x faster than state-of-the-art verifiers.
Neural Networks (NNs) have been extensively used for a wide spectrum of real-world regression tasks, where the goal is to predict a numerical outcome such as revenue, effectiveness, or a quantitative result. In many such tasks, the point prediction is not enough: the uncertainty (i.e. risk or confidence) of that predic…
Deep learning models can adaptively estimate functions with varying smoothness using regularization.
problem Estimating functions with heterogeneous smoothness in Besov or BV classes.
method Introduced a Parallel NN variant of deep ReLU networks with ℓ2 regularization equivalent to promoting ℓp-sparsity. result Achieves minimax rates for Besov and BV classes with exponentially closer performance as depth increases.
Study shows neural networks learn low frequencies first, proposing solutions.
problem Frequency bias in neural network learning process.
method Developed a PDE to unravel frequency dynamics, used Fourier Features model.
result Appropriate weight initialization can eliminate or control frequency bias.
This paper proposes the Mesh Neural Network (MNN), a novel architecture which allows neurons to be connected in any topology, to efficiently route information. In MNNs, information is propagated between neurons throughout a state transition function. State and error gradients are then directly computed from state updat…
Paper reveals hidden convexities in deep learning models using sparse signal processing.
problem Non-convex loss functions in deep learning models complicate optimization and theoretical understanding.
method Developed convex equivalences of ReLU NNs and their connections to sparse signal processing models.
result Recent research has uncovered hidden convexities in certain NN architectures, notably two-layer ReLU networks and other architectures.
Expressiveness and generalization of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to gradient similarity kernel, also known as Neural Tangent Kernel (NTK). In the majorit…
New method improves NN performance across various settings.
problem Improving neural network performance across different datasets and architectures.
method Population Gradients (PG) method to calculate non-local gradient estimates.
result Significantly improves final performance across architectures, data-sets, and hyper-parameters.
This paper removes the finite variance assumption for deep convolutional neural networks.
problem Removing the finite variance assumption for deep convolutional neural networks.
method Assuming iid parameters distributed according to a stable distribution, the paper shows that the infinite-channel limit of a deep feed-forward convolutional neural network is a multivariate stable stochastic process.
result The infinite-channel limit of a deep feed-forward convolutional neural network, under suitable scaling, is a multivariate stable stochastic process.
This work generalizes bounds on the number of linear regions in CPWL NNs.
problem Determining the number of linear regions in CPWL neural networks is challenging.
method Generalized bounds on the maximal number of linear regions for arbitrary CPWL activation functions.
result Depth significantly increases the number of linear regions, but not exponentially.
New method protects neural networks from adversarial attacks without generating adversarial examples.
problem Vulnerability of neural networks to adversarial examples.
method Entropic retraining, inspired by information theory.
result Significant increase in NNs' security and robustness.
DeepHybrid uses radar data to classify objects accurately.
problem Challenges in classifying objects using automotive radar sensors.
method Combines radar signal processing and Deep Learning; uses neural architecture search.
result Improves object classification performance compared to models using only spectra.
In this paper, a neural network-aided bit-interleaved coded modulation (NN-BICM) receiver is designed to mitigate the nonlinear clipping distortion in the LDPC coded direct currentbiased optical orthogonal frequency division multiplexing (DCOOFDM) systems. Taking the cross-entropy as loss function, a feed forward netwo…
Improved neural network models predict molecular and material properties efficiently.
problem Training neural networks for accurate interatomic potentials is computationally expensive.
method Gaussian moment-based neural networks with improved architecture and active learning.
result The new models achieve high accuracy and reduced training times.
New MIP methods improve training of integer-valued neural networks.
problem Training integer-valued neural networks with limited data and resources.
method Formulated new MIP models to optimize training efficiency and handle more data.
result Significantly outperforms previous state-of-the-art methods in accuracy, training time, and data usage.
Bucketed PCA-NN outperforms DNNs by 96% on MNIST.
problem Benchmarking deep neural networks for supervised classification.
method Applies PCA to individual buckets constructed in two phases, retains neural network architecture, and uses neurons that mirror input signals.
result Bucketed PCA-NN achieves 96% accuracy on MNIST, similar to DNNs.
We propose a tensor neural network (t-NN) framework that offers an exciting new paradigm for designing neural networks with multidimensional (tensor) data. Our network architecture is based on the t-product (Kilmer and Martin, 2011), an algebraic formulation to multiply tensors via circulant convolution. In this $t…
Neural network fusion reduces data acquisition costs for multi-fidelity sources.
problem Reducing cost in acquiring information from multiple data sources with varying fidelity.
method Employing a novel neural network architecture for nonlinear manifold learning of multi-fidelity data.
result Our approach provides high predictive power and quantifies various sources uncertainties.
New framework uses symmetry-based matrices for efficient, flexible NNs.
problem Designing neural networks with relaxed equivariance.
method Symmetry-based structured matrices, Group Matrices (GMs).
result GMs enable competitive performance with fewer parameters.
New method for explaining neural network activation functions.
problem Transparency in black-box deep learning algorithms.
method Symbolic explanation of activation functions using adaptive Gaussian Processes.
result Achieved partially explainable learning model with scalable topology.
Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable pe…
Convex neural networks enforce convex constraints on weights and activations, improving generalization.
problem Improving generalization and reducing overfitting in neural networks.
method Enforce convex constraints on weights and activations, using non-negative weights and non-decreasing convex activation functions.
result Convex neural networks self-regularize, outperforming base architectures and achieving similar performance to convolutional architectures.
RS-NN predicts belief functions for classification, improving accuracy and uncertainty estimation.
problem Improving confidence in machine learning predictions for safety-critical applications.
method Random-Set Neural Network (RS-NN) using random set mathematics.
result RS-NN outperforms state-of-the-art methods in accuracy, uncertainty estimation, and OoD detection.
Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the ℓp-norm threat model of the input instances, robustness verification against semantic adversarial attacks inducing large ℓp-norm perturbations,…