The Broad Impact of Feature Imitation: Neural Enhancements Across Financial, Speech, and Physiological Domains
This work demonstrates the broad utility of FINs for enhancing performance in diverse time-series domains, though it is incremental as it extends an existing method to new applications.
The study applied Feature Imitating Networks (FINs) to initialize neural network weights for approximating statistical features, testing them on Bitcoin price prediction, speech emotion recognition, and chronic neck pain detection, resulting in error reductions of around 1000 RMSE, accuracy increases of over 3%, and improvements of about 7%, respectively.
Initialization of neural network weights plays a pivotal role in determining their performance. Feature Imitating Networks (FINs) offer a novel strategy by initializing weights to approximate specific closed-form statistical features, setting a promising foundation for deep learning architectures. While the applicability of FINs has been chiefly tested in biomedical domains, this study extends its exploration into other time series datasets. Three different experiments are conducted in this study to test the applicability of imitating Tsallis entropy for performance enhancement: Bitcoin price prediction, speech emotion recognition, and chronic neck pain detection. For the Bitcoin price prediction, models embedded with FINs reduced the root mean square error by around 1000 compared to the baseline. In the speech emotion recognition task, the FIN-augmented model increased classification accuracy by over 3 percent. Lastly, in the CNP detection experiment, an improvement of about 7 percent was observed compared to established classifiers. These findings validate the broad utility and potency of FINs in diverse applications.