Neural prediction decorrelation reveals that adversarial robustness substantially improves DNN prediction accuracy across the entire human auditory cortex
Skrill, D.; Feather, J.; Norman-Haignere, S. V.
Show abstract
Sensory neuroscientists seek to model the neural computations that encode complex stimuli. Distinct encoding models often make similar predictions for natural stimuli such as speech, posing a challenge for model comparison. We developed a method to synthesize stimuli that decorrelate model predictions across a neural population, termed neural prediction decorrelation (NPD). Using fMRI responses to NPD sounds, we compared standard and adversarially robust deep neural network models of human auditory cortex. Prediction accuracy for NPD sounds was substantially better for the adversarially robust model in every region tested, an effect completely masked with natural sounds. Population responses to natural and synthesized NPD sounds shared an interpretable low-dimensional organization that was reproduced by the robust encoding model. NPD provides a general approach for comparing encoding models and reveals that adversarial robustness expands the predictive power of DNNs beyond natural stimuli, which is likely critical for targeting population activity through stimulus synthesis.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Model metamers illuminate divergences between biological and artificial neural networks 96%
- A large-scale, standardized physiological survey reveals higher order coding throughout the mouse visual cortex 95%
- Convolutional neural network models describe the encoding subspace of local circuits in auditory cortex 95%
Similar papers in this journal
Similar papers in this journal
- Parallel hierarchical encoding of linguistic representations in the human auditory cortex and recurrent automatic speech recognition systems 95%
- Improving Convolutional Network Interpretability with Exponential Activations 95%
- Modeling neural coding in the auditory midbrain with high resolution and accuracy 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.