The detection of algebraic auditory structures emerges with self-supervised learning
Fig 4
Decoding regular vs non-regular for each model layer.
Left: decoding accuracy of deviant versus original tones. The classifier is learned over all types of sequences and evaluation is separated across different types of sequences. The dataset are composed of 1000 sequences, with the 500 test sequences being the exact complementary to the training sequences (inversion of the role of each tone). Deviant tones are detected in earlier layers for simpler sequences. Right: earliest layer at which the decoding accuracy is maximal, for each type of sequence.