Computational Eco-Systems for Handwritten Digits Recognition
arXiv:1703.01872
Abstract
Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal. Our architecture could be summarized in two basic steps. First, we generate a diverse set of classification hypothesis using both Convolutional Neural Networks, currently the state-of-the-art technique for this task, among with other traditional and innovative machine learning techniques. Then, we optimally combine them through Meta-Nets, a family of recently developed and performing ensemble methods.
arXiv commentWithdrawn from Journal for flaws in methodology
References in corpus (5)
- Deep Learning in Neural Networks: An Overview
- Estimating Continuous Distributions in Bayesian Classifiers
- Computing the Stereo Matching Cost with a Convolutional Neural Network
- Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
- Batch-normalized Maxout Network in Network