Convergent evolution in neural representation space: emergent order in deep belief networks
Year: 2026
Type: article
Abstract: Deep Belief Networks (DBNs) learn hierarchical generative models without class supervision. We ask how this unsupervised hierarchy reorganizes data, whether it exposes latent class structure, and whether independently initialized networks discover corresponding internal representations. Across MNIST, Fashion-MNIST, and KMNIST, we follow class geometry and accessibility together with representational dimensionality, input reconstruction, and free generation. We find that global class organization generally strengthens with depth even though labels are never available during learning. Early layers frequently make class identity easier to extract, whereas deeper layers form increasingly compact representations in which related features are learned repeatedly. Global class geometry and classifier accessibility can nevertheless diverge, showing that a more ordered representation is not uniformly more informative at every class boundary. Independently trained DBNs converge to closely related depth-specific representation geometries and neuronal response features, indicating that the learned hierarchy is strongly constrained by the data and learning process. Deeper generative paths also produce broader populations of recognizable free samples while preserving less information about individual inputs. Together, these results show that unsupervised depth follows a reproducible path of representational reorganization in which class structure, accessibility, compression, reconstruction, and generation remain distinct but interacting properties.
Source: Frontiers in Complex Systems
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,353
Funder: Deutsche Forschungsgemeinschaft
Awards: G1312898290, G2830154102, G3506668107, G3963607356, G5241177577, G557459268, GRK 2839: Die Konstruktionsgrammatische Galaxis, G5713677572, Nutzung stochastischer Resonanzphänomene im zentralen auditorischen System zur Tinnitustherapie, G6777772083, G7315617606, Zwickerton und Tinnitus, Rekurrente neuronale Datenverarbeitung, gesteuert durch adaptives Rauschen und regulatorische Rückkopplung
OpenAlex ID: W7201866685