%0 Generic
%A Dold, Dominik
%C Heidelberg
%D 2020
%F heidok:28374
%R 10.11588/heidok.00028374
%T Harnessing function from form: towards  bio-inspired artificial intelligence in  neuronal substrates
%U https://archiv.ub.uni-heidelberg.de/volltextserver/28374/
%X Despite the recent success of deep learning, the mammalian brain is still unrivaled when it comes  to interpreting complex, high-dimensional data streams like visual, auditory and somatosensory stimuli.  However, the underlying computational principles allowing the brain to deal with unreliable, high-dimensional  and often incomplete data while having a power consumption on the order of a few watt are still mostly  unknown.  In this work, we investigate how specific functionalities emerge from simple structures observed in the  mammalian cortex, and how these might be utilized in non-von Neumann devices like “neuromorphic  hardware”. Firstly, we show that an ensemble of deterministic, spiking neural networks can be shaped by  a simple, local learning rule to perform sampling-based Bayesian inference. This suggests a coding scheme  where spikes (or “action potentials”) represent samples of a posterior distribution, constrained by sensory  input, without the need for any source of stochasticity. Secondly, we introduce a top-down framework where  neuronal and synaptic dynamics are derived using a least action principle and gradient-based minimization.  Combined, neurosynaptic dynamics approximate real-time error backpropagation, mappable to mechanistic  components of cortical networks, whose dynamics can again be described within the proposed framework.  The presented models narrow the gap between well-defined, functional algorithms and their biophysical  implementation, improving our understanding of the computational principles the brain might employ.  Furthermore, such models are naturally translated to hardware mimicking the vastly parallel neural  structure of the brain, promising a strongly accelerated and energy-efficient implementation of powerful  learning and inference algorithms, which we demonstrate for the physical model system “BrainScaleS–1”.