Extended Data Fig. 6: Root mean-square error (RMSE) between simulated excitation patterns of the TL and CoNNear models reported as fraction of the TL excitation pattern maximum (cf. Fig. 3). | Nature Machine Intelligence

Extended Data Fig. 6: Root mean-square error (RMSE) between simulated excitation patterns of the TL and CoNNear models reported as fraction of the TL excitation pattern maximum (cf. Fig. 3).

From: A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applications

Extended Data Fig. 6

Using the PReLU activation function (a) leads to an overall high RMSE as this architecture failed to learn the level-dependent cochlear compression characteristics and filter shapes. The models using the tanh nonlinearity (b,c) did learn to capture the level-dependent properties of cochlear excitation patterns, and performed with errors below 5% for the frequency ranges and stimulus levels captured by the speech training data (for CFs below 5 kHz, and stimulation levels below 90 dB SPL) The RMSE increased above 5% for all architectures when evaluating its performance on 8- and 10-kHz excitation patterns. This decreased performance results from the limited frequency content of the TIMIT training material.

Back to article page