Journal
NEURON
Volume 103, Issue 6, Pages 967-979Publisher
CELL PRESS
DOI: 10.1016/j.neuron.2019.08.034
Keywords
-
Categories
Funding
- Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DoI/IBC) [D16PC00003]
- Lifelong Learning Machines (L2M) program of the Defense Advanced Research Projects Agency (DARPA) [HR0011-18-2-0025, R01 EY026927]
- NSF NeuroNex [1707400]
- NSF [IOS-1552868]
- Institutional Strategy of the University of Tubingen (Deutsche Forschungsgemeinschaft) [ZUK 63]
- Carl-Zeiss-Stiftung
- German Federal Ministry of Education and Research (BMBF) through the Tubingen AI Center [FKZ: 01IS18039A]
- DFG Cluster of Excellence Machine Learning - New Perspectives for Science [EXC 2064/1, 390727645]
- DFG [CRC 1233]
Ask authors/readers for more resources
Despite enormous progress in machine learning, artificial neural networks still lag behind brains in their ability to generalize to new situations. Given identical training data, differences in generalization are caused by many defining features of a learning algorithm, such as network architecture and learning rule. Their joint effect, called inductive bias,'' determines how well any learning algorithm-or brain-generalizes: robust generalization needs good inductive biases. Artificial networks use rather nonspecific biases and often latch onto patterns that are only informative about the statistics of the training data but may not generalize to different scenarios. Brains, on the other hand, generalize across comparatively drastic changes in the sensory input all the time. We highlight some shortcomings of state-of-the-art learning algorithms compared to biological brains and discuss several ideas about how neuroscience can guide the quest for better inductive biases by providing useful constraints on representations and network architecture.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available