17 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…
A Differentiable Atari VCS:A Complex, Fully Known Ground Truth for Explainable AI
Andreas Maier, Siming Bayer, Patrick Krauss
Explanation requires ground truth: to verify an account of a system we must know its inner functioning-just what is missing where explainable AI (XAI) is most needed. Systems we ca…
Ten Years of the Stochastic Resonance Model of Tinnitus: From Phantom Perception to Adaptive Sensory Optimization
Patrick Krauss, Achim Schilling
Subjective tinnitus - the perception of sound in the absence of an external acoustic stimulus - remains one of the most debated phenomena in auditory neuroscience. In 2016, the sto…
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…