Novel Approaches to Artificial Intelligence Development Based on the Nearest Neighbor Method
This addresses reliability and explainability issues in critical areas such as medicine and industrial management, though it appears incremental as it builds on existing nearest neighbor techniques.
The paper tackles fundamental limitations of neural networks like hallucination and high computational costs by proposing an alternative approach based on the nearest neighbors method with hierarchical clustering, which reduces hallucination effects and accelerates nearest neighbor searches by hundreds of times with only a slight accuracy reduction.
Modern neural network technologies, including large language models, have achieved remarkable success in various applied artificial intelligence applications, however, they face a range of fundamental limitations. Among them are hallucination effects, high computational complexity of training and inference, costly fine-tuning, and catastrophic forgetting issues. These limitations significantly hinder the use of neural networks in critical areas such as medicine, industrial process management, and scientific research. This article proposes an alternative approach based on the nearest neighbors method with hierarchical clustering structures. Employing the k-nearest neighbors algorithm significantly reduces or completely eliminates hallucination effects while simplifying model expansion and fine-tuning without the need for retraining the entire network. To overcome the high computational load of the k-nearest neighbors method, the paper proposes using tree-like data structures based on Kohonen self-organizing maps, thereby greatly accelerating nearest neighbor searches. Tests conducted on handwritten digit recognition and simple subtitle translation tasks confirmed the effectiveness of the proposed approach. With only a slight reduction in accuracy, the nearest neighbor search time was reduced hundreds of times compared to exhaustive search methods. The proposed method features transparency and interpretability, closely aligns with human cognitive mechanisms, and demonstrates potential for extensive use in tasks requiring high reliability and explainable results.