Semi-supervised convolutional extreme learning machine

Mahmood Yousefi-Azar, Mark D. McDonnell

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

10 Citations (Scopus)


We propose a scheme for training a neural network as an image classifier. The approach includes a very rapid unsupervised feature learning algorithm and a supervised technique. We show that convolving and downsampling clustered descriptors of image patches with each input image can provide more discriminative features compared to both pre-trained descriptors and randomly generated convolutional filters. The implemented algorithm to discover clusters centroids (i.e. k-means clustering) for color images is not restricted to only RGB and we show that the algorithm is appropriate for Lab color representations. We use the centroids for obtaining convolutional features. We also present a high performance extreme learning machine (ELM), which is a method characterized by low implementation complexity, and run-time, to classify the learned features. We show that the combination of the unsupervised feature learning with the ELM outperforms previous related models that use different feature representations fed into an ELM, on the CIFAR-10 and Google Street View House Number (SVHN) datasets.

Original languageEnglish
Title of host publicationIJCNN 2017
Subtitle of host publicationProceedings of the 2017 International Joint Conference on Neural Networks
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages7
ISBN (Electronic)9781509061822, 9781509061815
ISBN (Print)9781509061839
Publication statusPublished - 30 Jun 2017
Event2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, United States
Duration: 14 May 201719 May 2017


Conference2017 International Joint Conference on Neural Networks, IJCNN 2017
Country/TerritoryUnited States


Dive into the research topics of 'Semi-supervised convolutional extreme learning machine'. Together they form a unique fingerprint.

Cite this