Combining Deep Learning with Good Old-Fashioned Machine Learning
This work addresses image classification challenges for researchers and practitioners, but it is incremental as it builds on existing methods without introducing a new paradigm.
The authors tackled the problem of improving image classification performance by combining deep learning with traditional machine learning through a stacking-based framework, achieving consistent improvements across four datasets with 110 out of 120 experiments showing better results.
We present a comprehensive, stacking-based framework for combining deep learning with good old-fashioned machine learning, called Deep GOld. Our framework involves ensemble selection from 51 retrained pretrained deep networks as first-level models, and 10 machine-learning algorithms as second-level models. Enabled by today's state-of-the-art software tools and hardware platforms, Deep GOld delivers consistent improvement when tested on four image-classification datasets: Fashion MNIST, CIFAR10, CIFAR100, and Tiny ImageNet. Of 120 experiments, in all but 10 Deep GOld improved the original networks' performance.