A deep learning framework for neuroscience.

Richards BA
Lillicrap TP
Beaudoin P
Bengio Y
Bogacz R
Christensen A
Clopath C
Costa RP
de Berker A
Ganguli S
Gillon CJ
Hafner D
Kepecs A
Kriegeskorte N
Latham P
Lindsay GW
Miller KD
Naud R
Pack CC
Poirazi P
Roelfsema P
Sacramento J
Saxe A
Scellier B
Schapiro AC
Senn W
Wayne G
Yamins D
Zenke F
Zylberberg J
Therien D
Kording KP

In this paper, we discuss how neuroscience research could benefit from recent advances in artificial intelligence. New and sophisticated computer programs, known as artificial neural networks, can learn complex tasks like naming images, translating languages, or playing board games. We argue that the insights gained from studying artificial neural networks could provide a framework to investigate the mechanisms of learning in the real brain.

Scientific Abstract

Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In artificial neural networks, the three components specified by design are the objective functions, the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.

Elements of neural network design
The three core components of artificial neural network design. When designing artificial neural networks, researchers do not craft the specific computations performed by the network. Instead, they specify these three components: objective function, learning rule and architecture.
2019. Nat. Neurosci., 22:1761-1770.
Related Content
Salvatori T, Song Y, Xu Z, Lukasiewicz T, Bogacz R
In Proceedings of the 36th AAAI Conference on Artificial Intelligence‚ AAAI 2022 ‚Vancouver, BC, Canada, February 22--March 1‚ 2022 (Vol. 10177, pp. 507-524). AAAI Press.
Whittington JCR, Bogacz R
2019. Trends Cogn. Sci., 23, 235-250