Binding Dynamics in Rotating Features
In human cognition, the binding problem describes the open question of how the brain flexibly integrates diverse information into cohesive object representations. Analogously, in machine learning, there is a pursuit for models capable of strong generalization and reasoning by learning object-centric representations in an unsupervised manner. Drawing from neuroscientific theories, Rotating Features learn such representations by introducing vector-valued features that encapsulate object characteristics in their magnitudes and object affiliation in their orientations. The "$\chi$-binding" mechanism, embedded in every layer of the architecture, has been shown to be crucial, but remains poorly understood. In this paper, we propose an alternative "cosine binding" mechanism, which explicitly computes the alignment between features and adjusts weights accordingly, and we show that it achieves equivalent performance. This allows us to draw direct connections to self-attention and biological neural processes, and to shed light on the fundamental dynamics for object-centric representations to emerge in Rotating Features.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSimilar Papers 제목 키워드 기반
Binding Dancers Into Attractors
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. P…
Rotating Features for Object Discovery
The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing…
Learning Interpretable Dynamics from Images of a Freely Rotating 3D Rigid Body
In many real-world settings, image observations of freely rotating 3D rigid bodies, such as satellites, may be available when low-dimensional measurements are not. However, the high-dimensionality of image data precludes…
Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach
Prediction of protein-ligand binding affinity is a major goal in drug discovery. Generally, free energy gap is calculated between two states (e.g., ligand binding and unbinding). The energy gap implicitly includes the ef…
Dimensionality ReductionDrug DiscoveryInsights into the role of dynamical features in protein complex formation: the case of SARS-CoV-2 spike binding with ACE2
The functionality of protein-protein complexes is closely tied to the strength of their interactions, making the evaluation of binding affinity a central focus in structural biology. However, the molecular determinants u…