Maya-Manas: Oscillatory Thalamo-Cortical Gating for Class-Incremental Learning in Affective Spiking Neural Networks
Venkatesh Swaminathan · Zenodo (CERN European Organization for Nuclear Research) · 2026
Version 2 (2026-08-04). Revised to the NLL Universal Paper Format v6. The original text is retained in full; nothing has been deleted. Corrections appear as marked blocks placed at the section that carries the claim, and each one states what the paper said, what the data show, the corrected claim, why it happened, and what still stands. This version corrects the gate specification and the series-best claim.The paper describes a peak-alignment gate at 0.5, but config.py gates timesteps at 0.5 while plasticity/manas.py gates the consistency score at 0.3 — every published number came from the 0.3 path; and the "series-best BWT" compares across runs with different AA, while this paper's 15.19% is below P05's published 16.03%.The O-LIF implementation stands; condition B = A is now correctly described as a determinism check rather than a falsification test. Everything below this line is the original description from version 1. It is retained unchanged for the record. Where it conflicts with the corrections above, the corrections stand. Two framings it repeats have since been withdrawn in full — the Bhaya Quiescence Law and the Buddhi S-Curve. Both are addressed in Maya-Meta P1, now superseded, and in the self-audit of Maya-Meta P2. Maya-Manas introduces an oscillatory thalamo-cortical attention gate for class-incremental learning in spiking neural networks, drawing on the Sanskrit cognitive concept of Manas — the sensory-receiving, oscillating mind that filters stimuli before deeper processing occurs. The gate is implemented as a half-cycle cosine threshold schedule on a leaky integrate-and-fire layer, cycling from maximum suppression to full receptivity within each forward pass to replicate the biological rhythm by which thalamic relay neurons selectively open cortical columns to salient input. Across a five-condition ablation on Split-CIFAR-100, the oscillatory mechanism delivers measurable improvements in continual learning retention, with the Bhaya Quiescence Law (catastrophic forgetting ≤ 0.32%) and Buddhi S-Curve Determinism (R²=1.0000) both confirmed, consistent with results across the broader Maya Research Series. This work is the seventh paper in the Maya Core series — thirteen studies from Nexus Learning Labs, Bengaluru, implementing the Advaita Vedantic Antahkarana as computational primitives in spiking neural networks — and it extends the series architecture with a biologically grounded gating mechanism that intersects oscillatory thresholding with affective salience amplification. Series: Part of the Maya Research Series — 13 papers implementing the Advaita Vedantic Antahkarana as computational primitives in spiking neural networks. Bhaya Quiescence Law (β* ≤ 0.32%) and Buddhi S-Curve Determinism (R²=1.0000) confirmed across all papers. Links: GitHub Repository (private — to request access: email [email protected] with subject Code Access Request — Maya-Manas and your research context) | Interactive Dashboard | Full Series Index — venky2099.github.io Nexus Learning Labs, Bengaluru · UDYAM-KR-02-0122422 · BHASKAR IN-0526-9452JSORCID: 0000-0002-3315-7907 · VAIRAGYA_DECAY_RATE = 0.002315 — an ORCID-derived provenance mark, not an experimental parameter. Each paper's disclosure block states whether it reached a result in that paper.Canary: MayaNexusVS2026NLL_Bengaluru