1. Binary classification of spoken words with passive phononic metamaterials
- Author
-
Dubček, Tena, Moreno-Garcia, Daniel, Haag, Thomas, Omidvar, Parisa, Thomsen, Henrik R., Becker, Theodor S., Gebraad, Lars, Bärlocher, Christoph, Andersson, Fredrik, Huber, Sebastian D., van Manen, Dirk-Jan, Villanueva, Luis Guillermo, Robertsson, Johan O. A., and Serra-Garcia, Marc
- Subjects
Electrical Engineering and Systems Science - Signal Processing ,Condensed Matter - Disordered Systems and Neural Networks ,Computer Science - Emerging Technologies ,Computer Science - Sound ,Electrical Engineering and Systems Science - Audio and Speech Processing ,Physics - Applied Physics - Abstract
Mitigating the energy requirements of artificial intelligence requires novel physical substrates for computation. Phononic metamaterials have a vanishingly low power dissipation and hence are a prime candidate for green, always-on computers. However, their use in machine learning applications has not been explored due to the complexity of their design process: Current phononic metamaterials are restricted to simple geometries (e.g. periodic, tapered), and hence do not possess sufficient expressivity to encode machine learning tasks. We design and fabricate a non-periodic phononic metamaterial, directly from data samples, that can distinguish between pairs of spoken words in the presence of a simple readout nonlinearity; hence demonstrating that phononic metamaterials are a viable avenue towards zero-power smart devices., Comment: 13 pages, 11 figures
- Published
- 2021