Coordinate Matrix Machine: A Human-level Concept Learning to Classify Very Similar Documents

TL;DR

The paper introduces the Coordinate Matrix Machine (CM²), a small, energy-efficient model that learns from structural features to classify very similar documents with only one example per class, mimicking human concept learning.

Contribution

This work presents the novel CM² model that leverages structural features for one-shot document classification, offering a green, explainable, and high-performance alternative to deep learning.

Findings

Outperforms traditional vectorizers and deep models in accuracy with minimal data

Achieves human-level concept learning with one sample per class

Operates efficiently on CPU-only environments

Abstract

Human-level concept learning argues that humans typically learn new concepts from a single example, whereas machine learning algorithms typically require hundreds of samples to learn a single concept. Our brain subconsciously identifies important features and learns more effectively. Contribution: In this paper, we present the Coordinate Matrix Machine (CM$^2$). This purpose-built small model augments human intelligence by learning document structures and using this information to classify documents. While modern "Red AI" trends rely on massive pre-training and energy-intensive GPU infrastructure, CM$^2$ is designed as a Green AI solution. It achieves human-level concept learning by identifying only the structural "important features" a human would consider, allowing it to classify very similar documents using only one sample per class. Advantage: Our algorithm outperforms traditional vectorizers and complex deep learning models that require larger datasets and significant compute. By focusing on structural coordinates rather than exhaustive semantic vectors, CM$^2$ offers: 1. High accuracy with minimal data (one-shot learning) 2. Geometric and structural intelligence 3. Green AI and environmental sustainability 4. Optimized for CPU-only environments 5. Inherent explainability (glass-box model) 6. Faster computation and low latency 7. Robustness against unbalanced classes 8. Economic viability 9. Generic, expandable, and extendable