How to Build Marcus's Algebraic Mind: From Thagard's Brain--Mind Viewpoint

2026-07-17

AI Summary

Current connectionist models struggle to support variable manipulation, structured representations, and the distinction between individuals and categories, while recursive convolutional binding often suffers from information loss in deep recursion. This work proposes VaCoAl, a hyperdimensional architecture that leverages XOR-and-shift operations over GF(2) combined with primitive polynomial linear feedback shift registers to construct an exact, invertible, and non-commutative binding mechanism. For the first time, this approach unifies the three pillars of Marcus’s algebraic theory of mind with Thagard’s binding requirements, enabling invertible compositional binding at O(N) complexity. It supports multi-hop relational reasoning and post-hoc auditable compositional generalization, while mitigating information degradation in deep recursion through a Rescue-Rate phase-transition mechanism, offering an orthogonal solution for interpretable and reversible relational reasoning.

Abstract

Two critiques of connectionist cognition converge on one missing capacity. In The Algebraic Mind, Marcus isolated three components any architecture must support -- operations over variables, structured representations, and individuals distinct from kinds -- showed perceptrons support none, and left neural implementation as conjecture. In Brain-Mind, Thagard made binding the single mechanism assembling perception, emotion, consciousness, and self, but rested it on circular convolution, a lossy algebra that degrades under the recursion his account of self and emotion demands. We argue one substrate answers both. VaCoAl is a hyperdimensional architecture built on one primitive, XOR-and-shift over GF(2), on primitive-polynomial linear-feedback shift registers; PyVaCoAl is its extended realization, adding a multi-stage rescue circuit, million-dimensional scale, and a Rescue-Rate phase transition (SRAM-CAM hardware and low-power claim remain future work). Binding, Bind(R,F) = R $\oplus$ shift(F), is exactly reversible and non-commutative: it fills Marcus's open register algebra (Pillar 1), supports compositional bundling at fixed dimension (Pillar 2), and separates individuals from kinds (Pillar 3), while removing the depth-degradation that afflicts convolution at Thagard's deepest recursions. We make three scoped claims. Capability: exact reversible binding at O(N) yields compositional generalization with post-hoc auditability no lossy or learned substrate offers. Necessity: two independent cognitive-architecture programs and a biological circuit (dentate gyrus-CA3) requiring the same reversible-compositional algebra is evidence, by convergent evolution not biomimicry, that it is substrate-independent. Position: we do not claim to surpass LLMs; the substrate is orthogonal, supplying the reversible, auditable, multi-hop relational reasoning statistical embeddings structurally lack.

Problem

• algebraic mind
• binding
• structured representations
• reversible compositionality
• cognitive architecture

Innovation

• hyperdimensional computing
• reversible binding
• algebraic mind
• compositional representation
• XOR-and-shift