PhD Exit Seminar – Jordan Guerguiev (Richards Lab)

Towards biologically plausible gradient descent

 

Abstract

 

Synaptic plasticity is the primary physiological mechanism underlying learning in the brain. It is dependent on pre- and post-synaptic neuronal activities, and can be mediated by neuromodulatory signals. However, to date, computational models of learning that are based on pre- and post-synaptic activity and/or global neuromodulatory reward signals for plasticity have not been able to learn complex tasks that animals are capable of. In the machine learning field, neural network models with many layers of computations trained using gradient descent have been highly successful in learning difficult tasks with near-human level performance. To date, it remains unclear how gradient descent could be implemented in neural circuits with many layers of synaptic connections. The overarching goal of this thesis is to develop theories for how the unique properties of neurons can be leveraged to enable gradient descent in deep circuits and allow them to learn complex tasks.

The work in this thesis is divided into three projects. The first project demonstrates that networks of cortical pyramidal neurons, which have segregated apical dendrites and exhibit bursting behavior driven by dendritic plateau potentials, can in theory leverage these physiological properties to approximate gradient descent through multiple layers of synaptic connections. The second project presents a theory for how ensembles of pyramidal neurons can multiplex sensory and learning signals using bursting and short-term plasticity, in order to approximate gradient descent and learn complex visual recognition tasks that previous biologically inspired models have struggled with. The final project focuses on the fact that machine learning models implementing gradient descent assume symmetric feedforward and feedback weights, and presents a theory for how the spiking properties of neurons can enable them to align feedforward and feedback weights in a network.

As a whole, this work aims to bridge the gap between powerful algorithms developed in the machine learning field and our current understanding of learning in the brain. To this end, we develop novel theories into how neuronal circuits in the brain can coordinate the learning of complex tasks, and present a number of experimental predictions that are fruitful avenues for future experimental research.