2014/01/07 by David Balduzzi, Balduzzi, David
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Computer Science and Game Theory (cs.GT) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Neurons and Cognition (q-bio.NC) #cs.AI #cs.GT #cs.LG #cs.MA #q-bio.NC
paper · pdf · doi:10.48550/arxiv.1401.1465
To appear, AAMAS 2014
arxiv created 2014/01/07 · arxiv updated 2014/01/08
We investigate cortical learning from the perspective of mechanism design. First, we show that discretizing standard models of neurons and synaptic plasticity leads to rational agents maximizing simple scoring rules. Second, our main result is that the scoring rules are proper, implying that neurons faithfully encode expected utilities in their synaptic weights and encode high-scoring outcomes in their spikes. Third, with this foundation in hand, we propose a biologically plausible mechanism whereby neurons backpropagate incentives which allows them to optimize their usefulness to the rest of cortex. Finally, experiments show that networks that backpropagate incentives can learn simple tasks.