Response time of lateral predictive coding and benefits of modular structures

2026-04-22

AI Summary

This study addresses the response latency inherent in Lateral Predictive Coding (LPC) networks when extracting non-Gaussian latent features. By reconfiguring the network’s dynamic architecture and incorporating a sparse modular design, the proposed approach significantly reduces system response time while preserving predictive accuracy and information robustness. The method achieves, for the first time, response latencies approaching the theoretical lower bound and demonstrates that modular architectures can match the overall performance of fully connected networks. Through an explicit trade-off between energy cost and information robustness, the work establishes an optimized LPC network with a simpler structure and faster response, attaining state-of-the-art performance across multiple metrics—including feature detection capability, response speed, energy efficiency, and robustness.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Lateral predictive coding (LPC) is a simple theoretical framework to appreciate feature detection in biological neural circuits. Recent theoretical work [Huang et al., Phys.Rev.E 112, 034304 (2025)] has successfully constructed optimal LPC networks capable of extracting non-Gaussian hidden input features by imposing the tradeoff between energetic cost and information robustness, but the resulting dynamical systems of recurrent interactions can be very slow in responding to external inputs. We investigate response-time reduction in the present paper. We find that the characteristic response time of the LPC system can be minimized to closely approaching the lower-bound value without compromising the mean predictive error (energetic cost) and the information robustness of signal transmission. We further demonstrate that optimal LPC networks taking a modular structural organization with extensively reduced number of lateral interactions are equally excellent as all-to-all completely connected networks, in terms of feature detection performance, response time, energetic cost and information robustness.

Problem

• response time
• lateral predictive coding
• modular structures
• information robustness
• energetic cost

Innovation

• lateral predictive coding
• response time optimization
• modular neural networks
• information robustness
• energetic efficiency