作者
Blake A. Richards,Timothy Lillicrap,Philippe Beaudoin,Yoshua Bengio,Rafał Bogacz,Amelia J. Christensen,Claudia Clopath,Rui Ponte Costa,Archy O. de Berker,Surya Ganguli,Colleen J. Gillon,Danijar Hafner,Ádám Kepecs,Nikolaus Kriegeskorte,Peter E. Latham,Grace W. Lindsay,Kenneth D. Miller,Richard Naud,Christopher C. Pack,Panayiota Poirazi,Pieter R. Roelfsema,João Sacramento,Andrew Saxe,Benjamin Scellier,Anna C. Schapiro,Walter Senn,Greg Wayne,Daniel Yamins,Friedemann Zenke,Joel Zylberberg,Denis Thérien,Konrad Körding
摘要
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. A deep network is best understood in terms of components used to design it—objective functions, architecture and learning rules—rather than unit-by-unit computation. Richards et al. argue that this inspires fruitful approaches to systems neuroscience.