CIFAR

MaRDI QIDQ29713swMATHFDO

Official website https://www.cs.toronto.edu/~kriz/cifar.html

Cited in

(only showing first 100 items - show all)

• PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning
• Adversarial noise attacks of deep learning architectures: stability analysis via sparse-modeled signals
• LSALSA: accelerated source separation via learned sparse coding
• Sparse deep neural networks using \(L_{1,\infty}\)-weight normalization
• An iterative stacked weighted auto-encoder
• Hyperband: a novel bandit-based approach to hyperparameter optimization
• GADE: a generative adversarial approach to density estimation and its applications
• An inertial Newton algorithm for deep learning
• A spin glass model for the loss surfaces of generative adversarial networks
• Confident learning: estimating uncertainty in dataset labels
• Nonparametric guidance of autoencoder representations using label information
• Noise Robust Projection Rule for Klein Hopfield Neural Networks
• A mathematical motivation for complex-valued convolutional networks
• Global optimization based on active preference learning with radial basis functions
• An adaptive Polyak heavy-ball method
• Machine unlearning: linear filtration for logit-based classifiers
• Stabilize deep ResNet with a sharp scaling factor \(\tau\)
• Towards harnessing feature embedding for robust learning with noisy labels
• Recurrence of optimum for training weight and activation quantized networks
• Ada-boundary: accelerating DNN training via adaptive boundary batch selection
• Deep learning of CMB radiation temperature
• A comparative study of data-dependent approaches without learning in measuring similarities of data objects
• Sparse kernel deep stacking networks
• Drop-activation: implicit parameter reduction and harmonious regularization
• Understanding image representations by measuring their equivariance and equivalence
• Generative adversarial networks with joint distribution moment matching
• Qsun
• Distributed Bayesian learning with stochastic natural gradient expectation propagation and the posterior server
• Binary quantized network training with sharpness-aware minimization
• Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling
• Mean Field Analysis of Deep Neural Networks
• Moderate deviation and restricted equivalence functions for measuring similarity between data
• Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection
• Loss-sensitive generative adversarial networks on Lipschitz densities
• MgNet: a unified framework of multigrid and convolutional neural network
• Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
• A tale of three probabilistic families: discriminative, descriptive, and generative models
• Stochastic nested variance reduction for nonconvex optimization
• scientific article; zbMATH DE number 7626736 (Why is no real title available?)
• MINRES: from negative curvature detection to monotonicity properties
• Quaternion-valued recurrent projection neural networks on unit quaternions
• Discriminative clustering with representation learning with any ratio of labeled to unlabeled data
• Use of static surrogates in hyperparameter optimization
• Joint optimization of an autoencoder for clustering and embedding
• scientific article; zbMATH DE number 7306906 (Why is no real title available?)
• On data preconditioning for regularized loss minimization
• Multiobjective Tree-Structured Parzen Estimator
• Quasi-Newton methods for machine learning: forget the past, just sample
• \((1 + \varepsilon)\)-class classification: an anomaly detection method for highly imbalanced or incomplete data sets
• On the antiderivatives of \(x^p/(1 - x)\) with an application to optimize loss functions for classification with neural networks
• Black-box adversarial attacks by manipulating image attributes
• Pruning deep convolutional neural networks architectures with evolution strategy
• Splicing learning: a novel few-shot learning approach
• Manifold-based synthetic oversampling with manifold conformance estimation
• scientific article; zbMATH DE number 7306873 (Why is no real title available?)
• scientific article; zbMATH DE number 7306897 (Why is no real title available?)
• ESAE: Evolutionary Strategy-Based Architecture Evolution
• Efficient Evolutionary Neural Architecture Search (NAS) by Modular Inheritable Crossover
• Effect of depth and width on local minima in deep learning
• Distributed Deep Learning on Heterogeneous Computing Resources Using Gossip Communication
• A Derivative-Free Method for Structured Optimization Problems
• Deep neural networks motivated by partial differential equations
• Residual networks as flows of diffeomorphisms
• The relative performance of ensemble methods with deep convolutional neural networks for image classification
• An exact penalty approach for optimization with nonnegative orthogonality constraints
• Regularisation of neural networks by enforcing Lipschitz continuity
• Fractional spectral graph wavelets and their applications
• Understanding generalization error of SGD in nonconvex optimization
• Theoretical investigation of generalization bounds for adversarial learning of deep neural networks
• scientific article; zbMATH DE number 7387621 (Why is no real title available?)
• Linear feature transform and enhancement of classification on deep neural network
• Dictionary learning for fast classification based on soft-thresholding
• Supervised t-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification
• Deep convolutional neural networks for image classification: a comprehensive review
• Probabilistic line searches for stochastic optimization
• Resolving learning rates adaptively by locating stochastic non-negative associated gradient projection points using line searches
• Unsupervised domain adaptation in the wild via disentangling representation learning
• Deep relaxation: partial differential equations for optimizing deep neural networks
• On Kernel Method–Based Connectionist Models and Supervised Deep Learning Without Backpropagation
• Mini-Batch Metropolis–Hastings With Reversible SGLD Proposal
• Analysis of classifiers' robustness to adversarial perturbations
• Search direction correction with normalized gradient makes first-order methods faster
• scientific article; zbMATH DE number 7370631 (Why is no real title available?)
• scientific article; zbMATH DE number 7370598 (Why is no real title available?)
• Extreme value theory for anomaly detection -- the GPD classifier
• A new initialization method based on normed statistical spaces in deep networks
• A game-based approximate verification of deep neural networks with provable guarantees
• Towards understanding sparse filtering: a theoretical perspective
• Deformable classifiers
• Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork
• scientific article; zbMATH DE number 7625162 (Why is no real title available?)
• Might a Single Neuron Solve Interesting Machine Learning Problems Through Successive Computations on Its Dendritic Tree?
• Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning
• Learning in the machine: random backpropagation and the deep learning channel
• Deep learning: an introduction for applied mathematicians
• Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines*
• Relative stability toward diffeomorphisms indicates performance in deep nets*
• ForestDSH: a universal hash design for discrete probability distributions
• Gaussian-spherical restricted Boltzmann machines
• CleanNet

This page was built for software: CIFAR