Timezone: »

Learning from brains how to regularize machines
Zhe Li · Wieland Brendel · Edgar Walker · Erick Cobos · Taliah Muhammad · Jacob Reimer · Matthias Bethge · Fabian Sinz · Xaq Pitkow · Andreas Tolias

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #65

Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input, e.g. adversarial noise leading to erroneous decisions. We propose to regularize CNNs using large-scale neuroscience data to learn more robust neural features in terms of representational similarity. We presented natural images to mice and measured the responses of thousands of neurons from cortical visual areas. Next, we denoised the notoriously variable neural activity using strong predictive models trained on this large corpus of responses from the mouse visual system, and calculated the representational similarity for millions of pairs of images from the model's predictions. We then used the neural representation similarity to regularize CNNs trained on image classification by penalizing intermediate representations that deviated from neural ones. This preserved performance of baseline models when classifying images under standard benchmarks, while maintaining substantially higher performance compared to baseline or control models when classifying noisy images. Moreover, the models regularized with cortical representations also improved model robustness in terms of adversarial attacks. This demonstrates that regularizing with neural data can be an effective tool to create an inductive bias towards more robust inference.

Author Information

Zhe Li (Baylor College of Medicine)
Wieland Brendel (AG Bethge, University of Tübingen)
Edgar Walker (Baylor College of Medicine)
Erick Cobos (Baylor College of Medicine)
Taliah Muhammad (Baylor College of Medicine)
Jacob Reimer (Baylor College of Medicine)
Matthias Bethge (University of Tübingen)
Fabian Sinz (University Tübingen)
Xaq Pitkow (BCM/Rice)
Andreas Tolias (Baylor College of Medicine)

More from the Same Authors