Implementation of Bayesian Fly Tracking Model using Analog Neuromorphic Circuits

There is a growing body of evidence that suggests that the neurons in the brain calculate the posterior probability of states and events based on observations provided by the sensory neurons. Based on this hypothesis, a neuromorphic framework is proposed, where the sensory neurons of the dragonfly make noisy observations of the fruit fly and uses the underlying Hidden Markov Model (HMM) to track the fruit fly in two dimensional space. The dragonfly estimates the target position by solving the Bayesian recursive equations online. This work presents a novel approach for implementing probabilistic networks using sub-threshold analog neuromorphic circuits, with the ability to perform the computation in real-time. This framework will pave the way to build complex probabilistic algorithms based on HMMs for low power real-time applications.

I. INTRODUCTION

Bayesian systems find numerous applications in object tracking [1] - [3], source localization [4], video analytics [5] etc.. Also, there is a growing body of evidence that suggests that the neurons in the brain calculate the posterior probability of states and events based on observations provided by the sensory neurons [1]. These systems are usually implemented in software. But for large systems, a real time implementation using software model is not feasible. This mandates the need for hardware implementation and many existing works [6]-[8] have realized the same. Murray [7] has developed pulse based mixed signal neural circuits. Thakur et al. [8] [9] have implemented an FPGA based stochastic design.