Hierarchical feature binding in a spiking neural network model of the primate ventral visual pathway
Brian Gardner, Patrick T. McCarthy, Joseph Chrol-Cannon, Dan F. M. Goodman, Simon R. Schultz, Giovanni Lo Iacono, Simon M. Stringer, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo · 2026
Read Hierarchical feature binding in a spiking neural network model of the primate ventral visual pathway by Brian Gardner, Patrick T. McCarthy, Joseph Chrol-Cannon, Dan F. M. Goodman, Simon R. Schultz, Giovanni Lo Iacono, Simon M. Stringer, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13581216.txt.
Description
Brian Gardner and co-authors test a brain-like network that learns which visual features belong together in a 2026 paper. Seeing a cup as one thing, not loose parts, is called feature binding. How neurons do it, in layers, is unsolved.
Their idea, binding by polychrony, uses groups of neurons that fire in exact timed chains. Repeated chains could store how features nest inside objects. The team built a spiking network shaped like the primate vision path, with up, down, and side links. Shown sets of related 2D shapes, the network taught itself. Single neurons came to answer for set shape features. The study tests whether timed firing can carry layered object structure.
Catalog record
| CREATOR | Brian Gardner, Patrick T. McCarthy, Joseph Chrol-Cannon, Dan F. M. Goodman, Simon R. Schultz, Giovanni Lo Iacono, Simon M. Stringer, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo, Abigail Morrison, Daniele Marinazzo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 213 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |