Skip to Main content Skip to Navigation
Conference papers

Latency-Based Probabilistic Information Processing in Recurrent Neural Hierarchies

Alexander Gepperth 1, 2 Mathieu Lefort 1, 2
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : In this article, we present an original neural space/latency code, integrated in a multi-layered neural hierarchy, that offers a new perspective on probabilistic inference operations. Our work is based on the dynamic neural field paradigm that leads to the emergence of activity bumps, based on recurrent lateral interactions, thus providing a spatial coding of information. We propose that lateral connections represent a data model, i.e., the conditional probability of a "true" stimulus given a noisy input. We propose furthermore that the resulting attractor state encodes the most likely "true" stimulus given the data model, and that its latency expresses the confidence in this interpretation. Thus, the main feature of this network is its ability to represent, transmit and integrate probabilistic information at multiple levels so that to take near-optimal decisions when inputs are contradictory, noisy or missing. We illustrate these properties on a three-layered neural hierarchy receiving inputs from a simplified robotic object recognition task. We also compare the network dynamics to an explicit probabilistic model of the task, to verify that it indeed reproduces all relevant properties of probabilistic processing.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Alexander Gepperth Connect in order to contact the contributor
Submitted on : Sunday, December 28, 2014 - 3:48:02 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on: : Monday, March 30, 2015 - 4:15:55 PM


Files produced by the author(s)




Alexander Gepperth, Mathieu Lefort. Latency-Based Probabilistic Information Processing in Recurrent Neural Hierarchies. International Conference on Artificial Neural Networks (ICANN), Sep 2014, Hamburg, Germany. pp.715 - 722, ⟨10.1007/978-3-319-11179-7_90⟩. ⟨hal-01098699⟩