CIFAR-10: KNN-based Ensemble of Classifiers
arXiv:1611.04905
Abstract
In this paper, we study the performance of different classifiers on the CIFAR-10 dataset, and build an ensemble of classifiers to reach a better performance. We show that, on CIFAR-10, K-Nearest Neighbors (KNN) and Convolutional Neural Network (CNN), on some classes, are mutually exclusive, thus yield in higher accuracy when combined. We reduce KNN overfitting using Principal Component Analysis (PCA), and ensemble it with a CNN to increase its accuracy. Our approach improves our best CNN model from 93.33% to 94.03%.
References in corpus (12)
- Improving neural networks by preventing co-adaptation of feature detectors
- Popular Ensemble Methods: An Empirical Study
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Empirical Evaluation of Rectified Activations in Convolutional Network
- Wide Residual Networks
- Deep Learning using Linear Support Vector Machines
- Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
- Learning Activation Functions to Improve Deep Neural Networks
- Fractional Max-Pooling
- ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
- Improving Deep Neural Networks with Probabilistic Maxout Units
- Batch-normalized Maxout Network in Network