Abstract
Discriminating distinct objects and concepts from sensory stimuli is essential for survival. Our brains accomplish this feat by forming disentangled internal representations in deep sensory networks shaped through experience-dependent synaptic plasticity. To elucidate the principles that underlie sensory representation learning, we derive a local plasticity model that shapes latent representations to predict future activity. This Latent Predictive Learning (LPL) rule conceptually extends Bienenstock-Cooper-Munro (BCM) theory by unifying Hebbian plasticity with predictive learning. We show that deep neural networks equipped with LPL develop disentangled object representations without supervision. The same rule accurately captures neuronal selectivity changes observed in the primate inferotemporal cortex in response to altered visual experience. Finally, our model generalizes to spiking neural networks and naturally accounts for several experimentally observed properties of synaptic plasticity, including metaplasticity and spike-timing-dependent plasticity (STDP). We thus provide a plausible normative theory of representation learning in the brain while making concrete testable predictions.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
This manuscript version now contains additional results on Latent Predictive Learning in spiking neural networks in which lateral inhibition and inhibitory plasticity implement neuronal decorrelation.
