Computational Eco-Systems for Handwritten Digits Recognition
This work addresses digit recognition accuracy, but it is incremental as it builds on existing ensemble methods.
The paper tackles handwritten digit recognition by generating diverse classification hypotheses using CNNs and other ML techniques, then optimally combining them with Meta-Nets, achieving improved performance.
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.