Enhancing classification accuracy through chaos
This addresses classification accuracy for moderate-dimensional data, but it is incremental as it builds on existing methods with a novel twist.
The paper tackles classification by using chaotic dynamical systems to evolve data in a higher-dimensional space, showing that this approach accelerates training and improves accuracy compared to standard softmax classifiers on perturbed orthogonal vectors.
We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as initial conditions for the evolution of a chaotic dynamical system for a prescribed temporal interval. The evolved state of the dynamical system is then fed to a trainable softmax classifier which outputs the probabilities of the various classes. As proof-of-concept, we use samples of randomly perturbed orthogonal vectors of moderate dimension (2 to 20), with a corresponding number of classes equal to the vector dimension, and show how our approach can both significantly accelerate the training process and improve the classification accuracy compared to a standard softmax classifier which operates on the original vectors, as well as a softmax classifier which only lifts the vectors to a higher-dimensional space without evolving them. We also provide an explanation for the improved performance of the chaos-enhanced classifier.