تقرير
Binding Dynamics in Rotating Features
العنوان: | Binding Dynamics in Rotating Features |
---|---|
المؤلفون: | Löwe, Sindy, Locatello, Francesco, Welling, Max |
سنة النشر: | 2024 |
المجموعة: | Computer Science Quantitative Biology |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Quantitative Biology - Neurons and Cognition |
الوصف: | 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. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2402.05627 |
رقم الأكسشن: | edsarx.2402.05627 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!