The Neural Particle Filter
Anna Kutschireiter, Simone Carlo Surace, Henning Sprekeler,, Jean-Pascal Pfister

TL;DR
The paper introduces the Neural Particle Filter, a weightless neural network model that performs nonlinear Bayesian filtering for dynamic perception, aligning with neural plausibility and improving performance in high-dimensional problems.
Contribution
It presents a novel weightless particle filter model that can be implemented by neural networks, bridging computational Bayesian filtering with biological plausibility.
Findings
The Neural Particle Filter accurately performs online state estimation.
It outperforms traditional particle filters in high-dimensional spaces.
The model supports online learning and multisensory integration.
Abstract
The robust estimation of dynamically changing features, such as the position of prey, is one of the hallmarks of perception. On an abstract, algorithmic level, nonlinear Bayesian filtering, i.e. the estimation of temporally changing signals based on the history of observations, provides a mathematical framework for dynamic perception in real time. Since the general, nonlinear filtering problem is analytically intractable, particle filters are considered among the most powerful approaches to approximating the solution numerically. Yet, these algorithms prevalently rely on importance weights, and thus it remains an unresolved question how the brain could implement such an inference strategy with a neuronal population. Here, we propose the Neural Particle Filter (NPF), a weight-less particle filter that can be interpreted as the neuronal dynamics of a recurrently connected neural network…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural dynamics and brain function · Neural Networks and Applications · Blind Source Separation Techniques
