How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields

2026-05-20

AI Summary

This work addresses the longstanding challenge that conventional multilayer perceptrons fail to fulfill Marcus’s three core criteria for an algebraic mind—variable manipulation, representation of recursive structures, and distinction between individual and category representations—by introducing the PyVaCoAl/VaCoAl neurocognitive architecture. This framework uniquely maps all three criteria onto a deterministic algebraic basis over GF(2), employing XOR-and-shift as its fundamental primitive and leveraging primitive-polynomial linear feedback shift registers to achieve invertible variable binding, non-commutative compositional bundling, and segregated address spaces for individuals versus categories. The resulting end-to-end hyperdimensional computing system not only satisfies all three cognitive requirements but also substantially outperforms dominant 2001-era approaches such as tensor products and circular convolution, while naturally supporting counterfactual reasoning at Pearl’s third level of causal inference.

Abstract

In The Algebraic Mind, Gary Marcus identified three components essential for any adequate cognitive architecture: operations over variables, recursively structured representations, and a distinction between mental representations of individuals and kinds. He argued that standard multilayer perceptrons supported none of these, acknowledging that a neural implementation using registers and treelets, constructed via developmental programs rather than gradient descent, remained a programmatic conjecture. Twenty-five years later, the required substrate is now available. Our newly developed PyVaCoAl/VaCoAl is a hyperdimensional computing architecture organized end-to-end around a single algebraic primitive: XOR-and-shift over GF(2), implemented by primitive-polynomial linear-feedback shift registers. The architecture supports reversible variable binding via Bind(R,F) = R XOR shift(F), non-commutative compositional bundling that distinguishes "the dog bites the man" from "the man bites the dog," and address-space individual/kind separation under the same algebra. A companion perspective argues that the dentate gyrus-CA3 circuit is a biological homologue of this same engine, with developmentally specified mossy-fiber targeting supplying the innate microcircuitry Marcus anticipated. In this paper, we map the correspondence between Marcus's three pillars and the operational commitments of PyVaCoAl/VaCoAl. We reinterpret the treelet as an algebraic register set indexed by a primitive generator polynomial, arguing that this architecture provides a functional neural substrate meeting Marcus's specifications far more closely than the tensor products, circular convolution, or temporal synchrony available in 2001. We also demonstrate how this substrate naturally extends to Pearl's rung-3 counterfactual reasoning, a capability the original treelet program did not directly target.

Problem

• cognitive architecture
• variable binding
• recursive representations
• individuals vs. kinds
• neural substrate

Innovation

• hyperdimensional computing
• Galois fields
• variable binding
• cognitive architecture
• counterfactual reasoning