Exploring the possibility of improving computer engineering methods through the study of biology, as certain biological processes have the ability to store memories and hold volatile RAM in the electrical state which has yet to be implemented in computer science.
Plasticity mechanisms in the brain extend beyond just weight update and can occur on shorter timescales than previously thought, including homeostasis adaptation and other yet to be discovered mechanisms. These discoveries could lead to improvements in machine learning algorithms and a better understanding of how the brain learns and adapts.
The dynamics of the synapse change is going on all the time, but there's a dynamic system in which you can say that the synapses don't change much during a computation. It is important to consider both the synaptic and system dynamics to model neurobiology.
This podcast discusses the concept of meta-learning, where one learning algorithm creates another, its historical applications in neuroscience, and how it is being used in deep learning today.
All cells in our body, including somatic and stem cells, form electrical networks during embryogenesis. Planaria hold the answer to deep questions and have been around for 400 million years.