Connecting Ifá Divination Architecture with Machine Learning Prediction Pipelines: Explicit Calculations, Full Derivations, and a Hybrid Framework

This paper presents a complete mathematical correspondence between the Yoruba Ifá knowledge system and the standard supervised machine-learning prediction pipeline. All central calculations are written explicitly: the derivation that eight binary positions produce exactly 256 odù, the expanded forms of mean-squared error and binary cross-entropy together with their gradients, the layer-wise equations of backpropagation, the formula for Expected Calibration Error, and the routing, retrieval and attestation equations of a hybrid architecture. The exposition is self-contained, implementation-ready, and prepared for publication. It demonstrates how discrete addressing and mandatory interpretation—long present in Ifá—can be combined with gradient-based optimization to produce more auditable and accountable predictive systems.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24374165
Primary Topic
Artificial Intelligence Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Connecting Ifá Divination Architecture with Machine Learning Prediction Pipelines: Explicit Calculations, Full Derivations, and a Hybrid Framework

Abdulrahman Mansur O
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence Applications
preprint

Connecting Ifá Divination Architecture with Machine Learning Prediction Pipelines: Explicit Calculations, Full Derivations, and a Hybrid Framework

Abdulrahman Mansur O
preprint en

Abstract

This paper presents a complete mathematical correspondence between the Yoruba Ifá knowledge system and the standard supervised machine-learning prediction pipeline. All central calculations are written explicitly: the derivation that eight binary positions produce exactly 256 odù, the expanded forms of mean-squared error and binary cross-entropy together with their gradients, the layer-wise equations of backpropagation, the formula for Expected Calibration Error, and the routing, retrieval and attestation equations of a hybrid architecture. The exposition is self-contained, implementation-ready, and prepared for publication. It demonstrates how discrete addressing and mandatory interpretation—long present in Ifá—can be combined with gradient-based optimization to produce more auditable and accountable predictive systems.

Zenodo (CERN European Organization for Nuclear Research)
Federal University Dutsin-Ma (NG)
Artificial Intelligence Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon