Consciousness is entailed by compositional learning of new causal structures in deep predictive processing systems (2301.07016v3)

Abstract: Machine learning algorithms have achieved superhuman performance in specific complex domains. However, learning online from few examples and compositional learning for efficient generalization across domains remain elusive. In humans, such learning includes specific declarative memory formation and is closely associated with consciousness. Predictive processing has been advanced as a principled Bayesian framework for understanding the cortex as implementing deep generative models for both sensory perception and action control. However, predictive processing offers little direct insight into fast compositional learning or of the separation between conscious and unconscious contents. Here, propose that access consciousness arises as a consequence of a particular learning mechanism operating within a predictive processing system. We extend predictive processing by adding online, single-example new structure learning via hierarchical binding of unpredicted inferences. This system learns new causes by quickly connecting together novel combinations of perceptions, which manifests as working memories that can become short- and long-term declarative memories retrievable by associative recall. The contents of such bound representations are unified yet differentiated, can be maintained by selective attention and are globally available. The proposed learning process explains contrast and masking manipulations, postdictive perceptual integration, and other paradigm cases of consciousness research. 'Phenomenal conscious experience' is how the learning system transparently models its own functioning, giving rise to perceptual illusions underlying the meta-problem of consciousness. Our proposal naturally unifies the feature binding, recurrent processing, predictive processing, and global workspace theories of consciousness.