A survey of deep network techniques all classifiers can adopt

DOI10.1007/S10618-020-00722-8MaRDI QIDQ2659274zbMATH OpenOpenAlexFDO

Authors Alireza Ghods, Diane J. Cook

Publication date 26 March 2021

Published in Data Mining and Knowledge Discovery (Search for Journal in Brave)

Full work available at URL https://europepmc.org/articles/pmc8475790

zbMATH Keywords

deep learningdeep neural networksoptimizationregularization

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07)

Recommendations

• A review of deep learning
• Deep learning of support vector machines with class probability output networks
• Deep learning: methods and applications
• Deep learning for time series classification: a review
• Optimization problems for machine learning: a survey

Cites work

• A comparative study of the leading machine learning techniques and two new optimization algorithms
• A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms
• A Fast Learning Algorithm for Deep Belief Nets
• A feature selection Newton method for support vector machine classification
• Adaptive subgradient methods for online learning and stochastic optimization
• Advanced Lectures on Machine Learning
• Bagging predictors
• Boosting a weak learning algorithm by majority
• Canonical Correlation Analysis: An Overview with Application to Learning Methods
• Deep learning
• Derivative-free optimization: a review of algorithms and comparison of software implementations
• Embedding Visual Hierarchy With Deep Networks for Large-Scale Visual Recognition
• Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition
• Greedy function approximation: A gradient boosting machine.
• How deep are deep Gaussian processes?
• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 1288299 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• scientific article; zbMATH DE number 3314813 (Why is no real title available?)
• Learning deep architectures for AI
• Learning to represent spatial transformations with factored higher-order Boltzmann machines
• Randomizing outputs to increase prediction accuracy
• Reducing the Dimensionality of Data with Neural Networks
• Stochastic gradient boosting.
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties

Cited in

(7)

• Optimizing non-decomposable measures with deep networks
• Linear feature transform and enhancement of classification on deep neural network
• Localized learning: a possible alternative to current deep learning techniques
• Convolutional neural network learning for generic data classification
• A review of deep learning
• Community detection-based deep neural network architectures: a fully automated framework based on Likert-scale data
• Deep learning of support vector machines with class probability output networks

Describes a project that uses

Uses Software

• CyCADA
• SketchyGAN
• darch
• AlexNet
• MNIST
• DNdisorder
• Adam
• AdaGrad
• GNMT
• MultiMin
• ImageNet
• AutoAugment
• C4.5
• CIFAR
• DeepFace

This page was built for publication: A survey of deep network techniques all classifiers can adopt

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2659274)