MNIST

swMATH12859MaRDI QIDQ24783FDOQ24783

Author name not available (Why is that?)

Cited In (only showing first 100 items - show all)

• Generative adversarial networks with decoder-encoder output noises
• Training of deep neural networks for the generation of dynamic movement primitives
• Vulnerability of classifiers to evolutionary generated adversarial examples
• Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter
• Adversarial noise attacks of deep learning architectures: stability analysis via sparse-modeled signals
• Title not available (Why is that?)
• The loss surfaces of neural networks with general activation functions
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Simplified energy landscape for modularity using total variation
• Development of an algorithm for reconstruction of droplet history based on deposition pattern using computational fluid dynamics and convolutional neural network
• On recovery guarantees for one-bit compressed sensing on manifolds
• Convergence of stochastic gradient descent in deep neural network
• IQN: an incremental quasi-Newton method with local superlinear convergence rate
• Local regularization of noisy point clouds: improved global geometric estimates and data analysis
• Title not available (Why is that?)
• A dimension reduction technique for large-scale structured sparse optimization problems with application to convex clustering
• Kernel flows: from learning kernels from data into the abyss
• Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning
• Convex programming based spectral clustering
• Title not available (Why is that?)
• Cautious active clustering
• Efficient set-valued prediction in multi-class classification
• Scaling description of generalization with number of parameters in deep learning
• Data-driven algorithm selection and tuning in optimization and signal processing
• A stochastic subgradient method for distributionally robust non-convex and non-smooth learning
• An implicit memory-based method for supervised pattern recognition
• Convex optimization learning of faithful Euclidean distance representations in nonlinear dimensionality reduction
• MODES: model-based optimization on distributed embedded systems
• Quick-means: accelerating inference for K-means by learning fast transforms
• SPEED: secure, private, and efficient deep learning
• Evaluation metrics for conditional image generation
• Consensus guided incomplete multi-view spectral clustering
• MimicGAN: robust projection onto image manifolds with corruption mimicking
• EGC: entropy-based gradient compression for distributed deep learning
• Interpretable machine learning: fundamental principles and 10 grand challenges
• Hybrid tensor decomposition in neural network compression
• Neural networks and deep learning. A textbook
• Mini-batch learning of exponential family finite mixture models
• Landscape and training regimes in deep learning
• Optimization of neural network training for image recognition based on trigonometric polynomial approximation
• A comprehensive survey and analysis of generative models in machine learning
• Learning context-dependent choice functions
• Bayesian distillation of deep learning models
• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm
• Nonlinearly preconditioned optimization on Grassmann manifolds for computing approximate Tucker tensor decompositions
• Joint dimensionality reduction and metric learning for image set classification
• Search for the global extremum using the correlation indicator for neural networks supervised learning
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
• Double data piling leads to perfect classification
• Topological measurement of deep neural networks using persistent homology
• Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
• Scheduled restart momentum for accelerated stochastic gradient descent
• A weight initialization based on the linear product structure for neural networks
• Fully hyperbolic convolutional neural networks
• How does momentum benefit deep neural networks architecture design? A few case studies
• Dualize, split, randomize: toward fast nonsmooth optimization algorithms
• Solution of physics-based Bayesian inverse problems with deep generative priors
• Towards out of distribution generalization for problems in mechanics
• Echo state network activation function based on bistable stochastic resonance
• Disentangled Representation Learning and Generation With Manifold Optimization
• Approximating morphological operators with part-based representations learned by asymmetric auto-encoders
• Modified Cheeger and ratio cut methods using the Ginzburg–Landau functional for classification of high-dimensional data
• Multidimensional scaling of noisy high dimensional data
• Variance-based single-call proximal extragradient algorithms for stochastic mixed variational inequalities
• Tropical coordinates on the space of persistence barcodes
• Probably correct \(k\)-nearest neighbor search in high dimensions
• Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training
• Drop-activation: implicit parameter reduction and harmonious regularization
• Deep learning model selection of suboptimal complexity
• Enhanced ensemble-based classifier with boosting for pattern recognition
• An improvement of the parameterized frequent directions algorithm
• A unifying framework of synaptic and intrinsic plasticity in neural populations
• Second-order stochastic optimization for machine learning in linear time
• Fast and Robust Learning by Reinforcement Signals: Explorations in the Insect Brain
• Uncertainty quantification in graph-based classification of high dimensional data
• High-dimensional dynamics of generalization error in neural networks
• Sequential changepoint detection in neural networks with checkpoints
• Hypocoercivity properties of adaptive Langevin dynamics
• Acceleration of hierarchical Bayesian network based cortical models on multicore architectures
• Title not available (Why is that?)
• Embedding sample points uncertainty measures in learning algorithms
• Title not available (Why is that?)
• Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork
• Approximate kernel partial least squares
• A random matrix approach to neural networks
• On the working set selection in gradient projection-based decomposition techniques for support vector machines
• Accurately computing the log-sum-exp and softmax functions
• A convolutional recursive modified self organizing map for handwritten digits recognition
• Global binary optimization on graphs for classification of high-dimensional data
• Title not available (Why is that?)
• A hybrid objective function for robustness of artificial neural networks -- estimation of parameters in a mechanical system
• Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation
• Stimulus space complexity determines the ratio of specialist and generalist neurons during pattern recognition
• Regularized greedy column subset selection
• Online multikernel learning based on a triple-norm regularizer for semantic image classification
• Spectral clustering with local projection distance measurement
• A stochastic semismooth Newton method for nonsmooth nonconvex optimization
• Analysis of the IJCNN 2007 agnostic learning vs. prior knowledge challenge
• Multilayer in-place learning networks for modeling functional layers in the laminar cortex
• Plug-and-play dual-tree algorithm runtime analysis

This page was built for software: MNIST