🤖 AI Summary
How does intelligence emerge through stable, persistent structures enabling memory, prediction, and semantic understanding under context-specific dynamics?
Method: Drawing on structural dynamics and the topological closure principle (∂² = 0), we formalize intelligence as sustained structural persistence Φ preceding contextual specificity Ψ. We introduce the Decoupling–Coupling Cycle (DEC) as the computational essence of sleep–wake cycles: context-decoupling operators (CDR → CIR) during sleep consolidate memories; context-coupling operators (CIR → CDR) during wakefulness drive perceptual learning. Using integral-transform operator design, neural-circuit functional abstraction, and inductive-bias-driven unsupervised direct fitting, we achieve unsupervised linearization of sensory memory.
Contribution/Results: This framework unifies memory consolidation, generalization capacity emergence, and internal model construction; formally links DEC to perception–action loops, perceptual control theory, and language-ecological origins; and proposes a novel brain-inspired computational paradigm for artificial intelligence.
📝 Abstract
Why do mammals need to sleep? Neuroscience treats sleep and wake as default and perturbation modes of the brain. It is hypothesized that the brain self-organizes neural activities without environmental inputs. This paper presents a new computational model of the sleep-wake cycle (SWC) for learning and memory. During the sleep mode, the memory consolidation by the thalamocortical system is abstracted by a disentangling operator that maps context-dependent representations (CDR) to context-independent representations (CIR) for generalization. Such a disentangling operator can be mathematically formalized by an integral transform that integrates the context variable from CDR. During the wake mode, the memory formation by the hippocampal-neocortical system is abstracted by an entangling operator from CIR to CDR where the context is introduced by physical motion. When designed as inductive bias, entangled CDR linearizes the problem of unsupervised learning for sensory memory by direct-fit. The concatenation of disentangling and entangling operators forms a disentangling-entangling cycle (DEC) as the building block for sensorimotor learning. We also discuss the relationship of DEC and SWC to the perception-action cycle (PAC) for internal model learning and perceptual control theory for the ecological origin of natural languages.