A Minimum Perturbation Theory of Deep Perceptual Learning
Preprint
Abstract
Perceptual learning (PL) involves long-lasting improvement in perceptual tasks following extensive training and is accompanied by modified neuronal responses in sensory cortical areas in the brain. Understanding the dynamics of PL and the resultant synaptic changes is important for causally connecting PL to the observed neural plasticity. This is theoretically challenging because learning-related changes are distributed across many stages of the sensory hierarchy. In this work, we modeled the sensory hierarchy as a deep nonlinear neural network and studied PL of fine discrimination, a common and well-studied paradigm of PL. Using tools from statistical physics, we developed a mean-field theory of the network in the limit of large number of neurons and large number of examples. Our theory suggests that, in this “thermodynamic” limit, the input-output function of the network can be exactly mapped to that of a deep linear network, allowing us to characterize the space of solutions for the task. Surprisingly, we found that modifications of synaptic weights in lower levels of the hierarchy are both sufficient and necessary for PL. To address the degeneracy of the space of solutions, we postulate that PL dynamics are constrained by a normative “minimum perturbation” (MP) principle, which favors weight matrices with minimal changes relative to their pre-learning values. Interestingly, MP plasticity induces changes to weights and neural representations in all layers of the network, except for the readout weight vector. In addition, such plasticity can be learned simply through slow learning. We further elucidate the properties of MP changes and compare them against experimental findings. Overall, our statistical mechanics theory of PL provides mechanistic and normative understanding of several important empirical findings of PL.Keywords
All Related Versions
- Published version: Physical Review E, 106 (6), 064406.
This publication has 55 references indexed in Scilit:
- An integrated reweighting theory of perceptual learningProceedings of the National Academy of Sciences, 2013
- Perceptual Learning Selectively Refines Orientation Representations in Early Visual CortexThe Journal of Neuroscience, 2012
- Perceptual Learning Reduces Interneuronal Correlations in Macaque Visual CortexNeuron, 2011
- Perceptual learning as improved probabilistic inference in early sensory areasNature Neuroscience, 2011
- The phenomenon of task-irrelevant perceptual learningVision Research, 2009
- Fine Discrimination Training Alters the Causal Contribution of Macaque Area MT to Depth PerceptionNeuron, 2008
- Neural correlates of perceptual learning in a sensory-motor, but not a sensory, cortical areaNature Neuroscience, 2008
- The Effect of Perceptual Learning on Neuronal Responses in Monkey Visual Area V4Journal of Neuroscience, 2004
- Neuronal Plasticity That Underlies Improvement in Perceptual PerformanceScience, 1994
- Improvement in line orientation discrimination is retinally local but dependent on cognitive setPerception & Psychophysics, 1992