Latency-based probabilistic information processing in a learning feedback hierarchy

Alexander Gepperth 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 study a three-layer neural hierarchy composed of bi-directionally connected recurrent layers which is trained to perform a synthetic object recognition task. The main feature of this network is its ability to represent, transmit and fuse probabilistic information, and thus to take near-optimal decisions when inputs are contradictory, noisy or missing. This is achieved by a neural space-latency code which is a natural consequence of the simple recurrent dynamics in each layer. Furthermore, the network possesses a feedback mechanism that is compatible with the space-latency code by making use of the attractor properties of neural layers. We show that this feedback mechanism can resolve/correct ambiguities at lower levels. As the fusion of feedback information in each layer is achieved in a probabilistically coherent fashion, feedback only has an effect if low-level inputs are ambiguous.
Document type :
Conference papers
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.inria.fr/hal-01098704
Contributor : Alexander Gepperth <>
Submitted on : Sunday, December 28, 2014 - 4:00:53 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Sunday, March 29, 2015 - 10:15:21 AM

File

gepperth2014latency.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Alexander Gepperth. Latency-based probabilistic information processing in a learning feedback hierarchy. International Joint Conference on Neural Networks (IJCNN), Jun 2014, Beijing, China. pp.3031 - 3037, ⟨10.1109/IJCNN.2014.6889919⟩. ⟨hal-01098704⟩

Share

Metrics

Record views

156

Files downloads

150