# Binding Dancers Into Attractors

arXiv: https://arxiv.org/abs/2206.02558 · HTML: https://mlsanity.com/paper/2206.02558/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 36 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture](https://mlsanity.com/paper/1809.07412/) (2018)
- [Active Tuning](https://mlsanity.com/paper/2010.03958/) (2020)
- [Many-Joint Robot Arm Control with Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2104.04064/) (2021)
- [Binding and Perspective Taking as Inference in a Generative Neural Network Model](https://mlsanity.com/paper/2012.05152/) (2020)

## Abstract (arXiv)

To effectively perceive and process observations in our environment, feature binding and perspective taking are crucial cognitive abilities. Feature binding combines observed features into one entity, called a Gestalt. Perspective taking transfers the percept into a canonical, observer-centered frame of reference. Here we propose a recurrent neural network model that solves both challenges. We first train an LSTM to predict 3D motion dynamics from a canonical perspective. We then present similar motion dynamics with novel viewpoints and feature arrangements. Retrospective inference enables the deduction of the canonical perspective. Combined with a robust mutual-exclusive softmax selection scheme, random feature arrangements are reordered and precisely bound into known Gestalt percepts. To corroborate evidence for the architecture's cognitive validity, we examine its behavior on the silhouette illusion, which elicits two competitive Gestalt interpretations of a rotating dancer. Our system flexibly binds the information of the rotating figure into the alternative attractors resolving the illusion's ambiguity and imagining the respective depth interpretation and the corresponding direction of rotation. We finally discuss the potential universality of the proposed mechanisms.