Journal
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
Volume 118, Issue 50, Pages -Publisher
NATL ACAD SCIENCES
DOI: 10.1073/pnas.2021925118
Keywords
efficient coding; synaptic plasticity; balanced state; neural sampling; dendritic computation
Categories
Funding
- Max-Planck-Society
- VolkswagenStiftung
- Bernstein Network
Ask authors/readers for more resources
This study introduces a new learning scheme based on voltage-dependent synaptic plasticity rules, which can learn efficient representations by locally balancing feedforward inputs. It overcomes the limitations of traditional Hebbian-like plasticity, particularly for complex high-dimensional inputs and inhibitory transmission delays. The results suggest the importance of dendritic excitatory-inhibitory balance and voltage-dependent synaptic plasticity in representation learning.
How can neural networks learn to efficiently represent complex and high-dimensional inputs via local plasticity mechanisms? Classical models of representation learning assume that feedforward weights are learned via pairwise Hebbian-like plasticity. Here, we show that pairwise Hebbian-like plasticity works only under unrealistic requirements on neural dynamics and input statistics. To overcome these limitations, we derive from first principles a learning scheme based on voltage-dependent synaptic plasticity rules. Here, recurrent connections learn to locally balance feedforward input in individual dendritic compartments and thereby can modulate synaptic plasticity to learn efficient representations. We demonstrate in simulations that this learning scheme works robustly even for complex high-dimensional inputs and with inhibitory transmission delays, where Hebbian-like plasticity fails. Our results draw a direct connection between dendritic excitatory-inhibitory balance and voltage-dependent synaptic plasticity as observed in vivo and suggest that both are crucial for representation learning.
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