Illari, Phyllis Kirstin; Grujičić, Bojana; (2025) Using Deep Neural Networks and Similarity Metrics to Predict and Control Brain Responses. In: Illari, Phyllis and Russo, Federica, (eds.) Routledge Handbook of Causality and Causal Methods. (pp. 392-405). Routledge: New York.

Text (Chapter 28 [Part V]) Illari_Using deep neural networks and similarity metrics to predict and control brain responses_AAM_chapter.pdf Access restricted to UCL open access staff Download (272kB)

Abstract

In the last ten years, there has been an increase in using artificial neural networks (ANNs) to model brain mechanisms, giving rise to a deep learning revolution in neuroscience. This chapter focuses on the ways convolutional ANNs have been used in visual neuroscience. A particular challenge in this developing field is the measurement of similarity between ANNs and the brain. We survey similarity measures neuroscientists use and analyze their merit for the goals of causal explanation, prediction, and control. In particular, we focus on two recent intervention-based methods of comparing ANNs and the brain that are based on linear mapping and analyze whether this is an improvement. While we conclude explanation has not been reached for reasons of underdetermination, progress has been made with regard to prediction and control.

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item