2024/05/27 by Anand Gopalakrishnan, Gopalakrishnan, Anand, Aleksandar Stanić +6 · 1 voice · 4 citations
Computer Science · #Artificial intelligence #Computer science #FOS: Computer and information sciences #Image Processing and 3D Reconstruction #Machine Learning (cs.LG) #Machine Learning and Data Classification #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Object (grammar) #Pattern recognition (psychology) #Unsupervised learning #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.2405.17283
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/05/27 · arxiv published 2024/05/27 · arxiv updated 2024/10/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a recurrent architecture with complex-valued weights. We propose a fully convolutional autoencoder, SynCx, that performs iterative constraint satisfaction: at each iteration, a hidden layer bottleneck encodes statistically regular configurations of features in particular phase relationships; over iterations, local constraints propagate and the model converges to a globally consistent configuration of phase assignments. Binding is achieved simply by the matrix-vector product operation between complex-valued weights and activations, without the need for additional mechanisms that have been incorporated into current synchrony-based models. SynCx outperforms or is strongly competitive with current models for unsupervised object discovery. SynCx also avoids certain systematic grouping errors of current models, such as the inability to separate similarly colored objects without additional supervision.