E. G. Reis

The Ψ-Former: Topological Downward Causation via Riemannian Optimization in Deep Neural Architectures

Zenodo (CERN European Organization for Nuclear Research) January 5, 2026 E. G. Reis

We propose the Ψ-Former 2.0, a deep learning architecture explicitly designed to approximate the structural conditions of consciousness as outlined in the Phenomenal Manifold Hypothesis (PMH). Current neural architectures, while powerful, lack the geometric and dynamical constraints necessary to instantiate a coherent phenomenal manifold Ψ — the geometric structure hypothesized to encode...