(Open Access) A Comparison of Optimization Algorithms for Deep Learning (2020) | Derya Soydaner | 110 Citations

A Comparison of Optimization Algorithms for Deep Learning

Authors: Derya Soydaner, Mimar Sinan Fine Arts University

• Date: 30 Apr 2020
• Journal: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 34, Iss: 13, pp 2052013
• DOI: 10.1142/S0218001420520138

TL;DR

The behaviour of the algorithms during training and results on four image datasets, namely, MNIST, CIFAR-10, Kaggle Flowers and Labeled Faces in the Wild are compared by pointing out their differences against basic optimization algorithms.

Abstract

In recent years, we have witnessed the rise of deep learning. Deep neural networks have proved their success in many areas. However, the optimization of these networks has become more difficult as ...

Citations

• Showing all 110 results

  • Journal Article Human activity recognition in artificial intelligence framework: a narrative review by Neha Gupta, Suneet K. Gupta, Rajesh Kumar Pathak, Vanita Jain, and Parisa Rashidi
  • TL;DR: In this article, a detailed narration on the three pillars of human activity recognition (HAR) is presented covering the period from 2011 to 2021, and the review presents the recommendations for an improved HAR design, its reliability, and stability.

• Proceedings Article Prediction of lung and colon cancer through analysis of histopathological images by utilizing Pre-trained CNN models with visualization of class activation and saliency maps by Satvik Garg and Somya Garg

  • TL;DR: In this paper, eight distinctive pre-trained CNN models, VGG16, NASNetMobile, InceptionV3, INceptionResNetV2, ResNet50, Xception, MobileNet, and DenseNet169 are trained on LC25000 dataset.

References

1. Very Deep Convolutional Networks for Large-Scale Image Recognition by Karen Simonyan and Andrew Zisserman

   • TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.

2. ImageNet classification with deep convolutional neural networks by Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton

   • TL;DR: A large, deep convolutional neural network was trained to classify images in the ImageNet LSVRC-2010 contest.