PrototypeML simplifies neural network design and development.
problem Error-prone code and time-consuming model design.
method Visual interface for neural networks, abstracting PyTorch.
result Reduces model design and development time, easier debugging.
Develops neural network for directed hypergraphs for node classification.
problem Irregular data structure, particularly directed graphs.
method Directed hypergraph neural network and semi-supervised learning method.
result Novel directed hypergraph neural network achieves highest accuracies on node classification tasks.
Unified platform SOCRATES for neural network analysis.
problem Analyzing neural networks for bugs and fairness.
method Standardized format, assertion language, and multiple analysis algorithms.
result Unified platform for neural network analysis.
While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data. Measures for characterizing and monitoring structural properties, however, have not been developed. In this work, we propose neural persistence, a complexity measure for ne…
Deep neural networks have been increasingly used in software engineering and program analysis tasks. They usually take a program and make some predictions about it, e.g., bug prediction. We call these models neural program analyzers. The reliability of neural programs can impact the reliability of the encompassing anal…
The study explores how brain development can inspire efficient deep learning models.
problem Efficient and robust optimization procedures for deep learning.
method Inspiration from biological neural development to improve deep learning models.
result Biological neural development can inspire efficient and robust optimization procedures.
Study uses neural networks to filter financial spillovers from noise.
problem Accurately measuring spillovers in financial markets from noise.
method Neural network-based denoising of covariance matrices.
result Developed markets are net transmitters of volatility spillovers, but can become receivers during stress.
In the last few years, we have seen the transformative impact of deep learning in many applications, particularly in speech recognition and computer vision. Inspired by Google's Inception-ResNet deep convolutional neural network (CNN) for image classification, we have developed "Chemception", a deep CNN for the predict…
Automates GNN design for molecular property prediction.
problem Designing and tuning GNN architectures for molecular property prediction is labor-intensive.
method Developed a NAS approach to automatically discover high-performing GNN architectures for MPNNs.
result Automatically discovered MPNNs outperform manually designed GNNs in molecular property prediction.
We introduce a new strategy designed to help physicists discover hidden laws governing dynamical systems. We propose to use machine learning automatic differentiation libraries to develop hybrid numerical models that combine components based on prior physical knowledge with components based on neural networks. In these…
Develops statistical guarantees for neural networks with regularization.
problem Lack of comprehensive mathematical theories for neural networks.
method General statistical guarantee for least-squares with regularizers.
result Prediction error increases sub-linearly in layers, logarithmically in parameters.
Graph neural networks help AI agents learn more complex language.
problem Understanding how AI agents learn and use language.
method Developed graph referential games to compare different AI models.
result Graph neural networks enable AI to learn more complex, compositional language.
Develops a new deep learning formulation using Mori-Zwanzig formalism.
problem Improves deep learning by introducing a new concept of memory.
method Uses Mori-Zwanzig formalism to propagate quantities of interest through neural networks.
result Rigorously transforms deep networks into shallow ones using decay property of memory operator.
Researchers develop neural networks for manifold data with a convergence rate.
problem Analyzing high-dimensional data on non-Euclidean domains.
method Constructing manifold neural networks using spectral decomposition of the Laplace Beltrami operator.
result Established a rate of convergence for the neural network scheme that depends on intrinsic manifold dimension.
SingleProp speeds up robust neural network training with minimal certification.
problem Efficiently defending neural networks against adversarial attacks with certified guarantees.
method SingleProp regularizer that requires only one forward pass per training iteration.
result Comparable certified accuracy to state-of-the-art defenses, but significantly faster training.
Gaussian processes are ubiquitous in nature and engineering. A case in point is a class of neural networks in the infinite-width limit, whose priors correspond to Gaussian processes. Here we perturbatively extend this correspondence to finite-width neural networks, yielding non-Gaussian processes as priors. The methodo…
Deep learning has enabled major advances in the fields of computer vision, natural language processing, and multimedia among many others. Developing a deep learning system is arduous and complex, as it involves constructing neural network architectures, managing training/trained models, tuning optimization process, pre…
A new faster neural network training method using backprojection.
problem Training feedforward neural networks more efficiently.
method Projection and reconstruction at each layer to force projected data and reconstructed labels to be similar.
result The proposed method is faster than backpropagation and gives insights into networks.
Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a neural network while changing its neural architecture, could be helpfu…
An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: what are the theoretical principles governing the ability of neural networks to acquire, or…
Neural network predicts optimal pension investments based on preferences.
problem Optimal pension investment problem with varying preferences.
method Used a neural network to identify optimal solutions to a family of investment problems.
result Validated network accuracy using classical numerical methods.
Develops variational Bayesian neural network for complex biomedical applications.
problem High computational cost of Markov Chain Monte Carlo in BNN.
method Variational Bayes inference for posterior consistency and classification accuracy.
result Developed statistical theory for posterior consistency and prediction accuracy.
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled th…
AgEBO-Tabular combines NAS and hyperparameter tuning for fast, high-performing tabular models.
problem Developing high-performing predictive models for large tabular data sets is challenging.
method Combines aging evolution NAS and asynchronous Bayesian optimization for hyperparameter tuning in data-parallel training.
result Automatically discovered neural network models outperform state-of-the-art AutoML ensembles in inference speed by two orders of magnitude.
Paper develops exact convex optimization for neural networks with polynomial activations.
problem Training two-layer neural networks with nonlinear polynomial activations.
method Exact convex optimization using semidefinite programming.
result Global optimization of neural networks is polynomial-time computable.
This review explores Convolutional Neural Networks in machine fault diagnosis.
problem Machine fault diagnosis is crucial for safe equipment operation and production.
method Comprehensive review of Convolutional Neural Network (CNN) applications in fault diagnosis.
result A systematic review of CNN-based fault diagnosis methods, covering data collection, model construction, and feature learning.
Develops vector-valued RKBS for neural networks and operators.
problem Understanding function spaces of Rd-valued neural networks and neural operators. method Defines and constructs vector-valued RKBS (vv-RKBS) without restrictive assumptions.
result Establishes Representer Theorem for neural architectures.
The paper develops a neural network-based method for detecting change points in large-scale time-evolving data.
problem Detecting and locating change points in multivariate time-evolving data.
method Two-step procedure involving neural network training and test error function calibration over moving windows.
result Consistent estimates for the number and locations of change points under temporal dependence.
Develops a new neural spike train decoding framework using topological data.
problem Decoding neural spike trains from head direction and grid cells.
method Combines simplicial complex discovery with deep learning to capture higher-order connectivity.
result Demonstrates effectiveness on head direction and trajectory prediction datasets.
This paper presents a constructive algorithm that achieves successful one-shot learning of hidden spike-patterns in a competitive detection task. It has previously been shown (Masquelier et al., 2008) that spike-timing-dependent plasticity (STDP) and lateral inhibition can result in neurons competitively tuned to repea…
GrADE uses graph neural networks and Neural ODE for solving time-dependent nonlinear PDEs efficiently.
problem Solving time-dependent nonlinear PDEs is computationally challenging and time-consuming.
method GrADE combines graph neural networks for spatial modeling and Neural ODE for temporal modeling, using attention mechanisms.
result GrADE efficiently solves PDEs, demonstrating scalability and better accuracy compared to existing methods.
Improved machine learning for reservoir optimization problems.
problem Optimizing control in high-dimensional storage problems.
method Modified dynamic programming algorithm with neural networks for Bellman values and conditional cuts.
result Neural networks outperform classical feedforward networks in estimating Bellman values.
Develops wavelet-based neural network approximation theory.
problem Analyzing neural network approximation capabilities over various activation functions.
method Wavelet frame theory on spaces of homogeneous type, sufficient conditions for approximation, error estimates.
result Derives sufficient conditions for neural networks to approximate any functions in a given space, including non-smooth activations.
New RL framework models continuous-time dynamics using neural ODEs.
problem Modeling continuous-time dynamics in semi-Markov decision processes.
method Model-based reinforcement learning with neural ODEs.
result High-performing policies developed with minimal data.
This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent vision and speech systems. With avai…
Develops neural networks that follow thermodynamics principles.
problem Learning physical systems from data while respecting thermodynamics.
method Uses feedforward neural networks and the GENERIC formalism to enforce metriplectic structure.
result Predictions comply with first and second principles of thermodynamics.
TF-GNN simplifies graph neural networks in TensorFlow.
problem Handling rich heterogeneous graph data in machine learning.
method A scalable library with a Keras message passing API.
result Enables low-code solutions for broader developers.
The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir Computing (RC) is gaining an increasing research attention in the neural networks community. The recently introduced Deep Echo State Network (DeepESN) model opened the way to an extremely efficient approach for designing deep neura…
Paper develops a neural-fuzzy controller for GPS-intelligent buoys.
problem Optimally track dynamically positioned marine buoys with unknown parameters.
method Dynamic system modeling using neural-fuzzy networks with backstepping technique.
result The controller minimizes position errors and adjusts buoy positions accurately.
Optimizes graph neural networks using natural gradient descent.
problem Improving efficiency and performance of graph neural networks.
method Employing natural gradient descent to optimize graph neural networks.
result Natural gradient optimization leads to superior performance compared to existing methods.
Develops exact convex optimization formulations for neural networks.
problem Training two-layer neural networks with rectified linear units.
method Uses semi-infinite duality and minimum norm regularization to develop exact convex optimization formulations.
result Shows equivalence of ReLU networks trained with weight decay to block ℓ1 penalized convex models. New technologies for recording the activity of large neural populations during complex behavior provide exciting opportunities for investigating the neural computations that underlie perception, cognition, and decision-making. Nonlinear state space models provide an interpretable signal processing framework by combinin…
Hybrid model improves weather forecasting accuracy.
problem Combining physics and machine learning for better weather predictions.
method Offline and online training of a neural network to correct model errors in the IFS.
result The hybrid model reduces forecast errors and improves accuracy.
LocalDrop uses local Rademacher complexity for neural network regularization.
problem Overfitting in deep neural networks.
method Developed a new regularization function based on local Rademacher complexity.
result Demonstrated effectiveness of LocalDrop through extensive experiments.
Develops framework for understanding deep learning in time series data.
problem Understanding and explaining decisions made by deep learning models in time series data.
method Uses deep neural networks to capture and explain temporal dependencies in time series data.
result Framework successfully captures and explains temporal dependencies in various synthetic and real-world datasets.
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop…
Develops deep learning for fast, accurate option pricing models.
problem Computational efficiency and accuracy in option pricing models.
method Neural network generators solving backward Kolmogorov equations for TPDFs.
result Ultra-fast, highly accurate option pricing models for various asset models.
We developed safe and ranged approximations for ReLU, tanh, and sigmoid functions to reduce neural network training time.
problem Expensive computation of hyperbolic tangent and sigmoid functions in neural networks.
method Function approximation techniques to create safe and ranged approximations.
result 10% to 37% improvement in training times on CPU and 20% to 53% improvement in ranged cases.