Browse/search for people

Publication - Dr Benjamin Evans

    Adding biological constraints to CNNs makes image classification more human-like and robust

    Citation

    Malhotra, G, Evans, BD & Bowers, JS, 2019, ‘Adding biological constraints to CNNs makes image classification more human-like and robust’. in: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany., pp. 256

    Abstract

    In this study, we show that when standard convolutional neural networks (CNNs) are trained end-to-end on datasets containing low-level and spatially high-frequency features, they are susceptible to learning these potentially idiosyncratic features if they are predictive of the output class. Such features are extremely unlikely to play a major role in human object recognition, where instead a strong preference for shape is observed. Through a series of empirical studies, we show that standard CNNs cannot overcome this reliance on non-shape features merely by making training more ecologically plausible or using standard regularisation methods. However, we show that these problems can be ameliorated by forgoing end-to-end learning and processing images initially with Gabor filters, in a manner that more closely resembles biological vision.

    Full details in the University publications repository