10 papers
Convergent Evolution in Neural Representation Space: Emergent Order in Deep Belief Networks
Patrick Krauss, Achim Schilling, Andreas Maier +2
Deep Belief Networks (DBNs) learn hierarchical generative models without class supervision. Here, we ask whether this purely unsupervised process nevertheless organizes internal re…
Convergent Evolution in Algorithmic Space
Patrick Krauss, Achim Schilling, Andreas Maier +4
In evolutionary biology, unrelated organisms can independently evolve similar structures when exposed to similar functional demands. Here we ask whether an analogous form of conver…
Surviving by Serving: Functional Relevance Drives Self-Organization in Complex Adaptive Systems
Claus Metzner, Ali Ghebleh, Achim Schilling +3
Complex adaptive systems often develop organized structures without centralized control. Yet the local mechanisms by which functional organization emerges and persists remain incom…
Word Class Representations Spontaneously Emerge from Successor Representations Trained on Natural Language
Mathis Immertreu, Achim Schilling, Thomas Kinfe +1
Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Represent…
Convergent Representations of Linguistic Constructions in Human and Artificial Neural Systems
Pegah Ramezani, Thomas Kinfe, Andreas Maier +2
Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial n…
Are cortical microcircuits optimized for information flux? -- A simulation-based reverse engineering study
Claus Metzner, Ali Ghebleh, Karin Prebeck +4
A sufficiently large information flux in recurrent neural networks, quantified by the mutual information between successive network states, is considered a prerequisite for rich in…