If deep learning is the answer, then what is the question?
arXiv:2004.07580
Abstract
Neuroscience research is undergoing a minor revolution. Recent advances in machine learning and artificial intelligence (AI) research have opened up new ways of thinking about neural computation. Many researchers are excited by the possibility that deep neural networks may offer theories of perception, cognition and action for biological brains. This perspective has the potential to radically reshape our approach to understanding neural systems, because the computations performed by deep networks are learned from experience, not endowed by the researcher. If so, how can neuroscientists use deep networks to model and understand biological brains? What is the outlook for neuroscientists who seek to characterise computations or neural codes, or who wish to understand perception, attention, memory, and executive functions? In this Perspective, our goal is to offer a roadmap for systems neuroscience research in the age of deep learning. We discuss the conceptual and methodological challenges of comparing behaviour, learning dynamics, and neural representation in artificial and biological systems. We highlight new research questions that have emerged for neuroscience as a direct consequence of recent advances in machine learning.
4 Figures, 17 Pages
References in corpus (14)
- Overcoming catastrophic forgetting in neural networks
- Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway
- Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
- Recurrence is required to capture the representational dynamics of the human visual system
- Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
- A mathematical theory of semantic development in deep neural networks
- Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
- MONet: Unsupervised Scene Decomposition and Representation
- Generative replay with feedback connections as a general strategy for continual learning
- Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
- Unsupervised Predictive Memory in a Goal-Directed Agent
- Early Visual Concept Learning with Unsupervised Deep Learning
- Controversial stimuli: pitting neural networks against each other as models of human recognition
- How can deep learning advance computational modeling of sensory information processing?