Jipeng Han

Jipeng Han

Contributions to AI: This paper proposes a neuro-symbolic search architecture integrating discrete rule-based logic with lightweight Neural Network Feedback Control (NNFC). Utilizing cascade filtering to isolate neural mispredictions while dynamically compensating for static heuristic biases, the framework theoretically guarantees search stability and efficiency in massive discrete state spaces. Contributions to Engineering Applications: The framework provides a scalable, divide-and-conquer solution coordinating heterogeneous rule-sets in knowledge-intensive industrial systems (e.g., multi-domain relational inference and symbolic derivation), eliminating maintenance bottlenecks and state-space explosion of monolithic reasoning engines. Modern industrial AI requires dynamic orchestration of modular domain logic, yet reliable cross-domain rule management remains lacking. We address this with Chain-Oriented Objective Logic (COOL), a high-performance neuro-symbolic framework introducing: (1) Chain-of-Logic (CoL), a divide-and-conquer paradigm partitioning complex reasoning into expert-guided, hierarchical sub-DSLs via runtime keywords; and (2) Neural Network Feedback Control (NNFC), a self-correcting mechanism using lightweight agents and a cascade filtering architecture to suppress erroneous predictions and ensure industrial-grade reliability. Theoretical analysis establishes complexity bounds and Lyapunov stability. Ablation studies on relational and symbolic tasks show CoL achieves 100% accuracy (70% improvement), reducing tree operations by 91% and accelerating execution by 95%. Under adversarial drift and forgetting, NNFC further improves accuracy and reduces computational cost by 64%.

Jipeng Han

While Landauer's principle establishes the fundamental thermodynamic floor for information erasure and Fisher Information provides a metric for local curvature in parameter space, these classical frameworks function effectively only as approximations within regimes of sparse rule-constraints. They fail to explain the super-linear, and often explosive, computational and energy costs incurred when maintaining symbolic interpretability during the reconfiguration of advanced intelligent systems. This paper introduces the property of intelligence inertia and its underlying physical principles as foundational characteristics for quantifying the computational weight of intelligence. We demonstrate that this phenomenon is not merely an empirical observation but originates from the fundamental non-commutativity between rules and states, a root cause we have formally organized into a rigorous mathematical framework. By analyzing the growing discrepancy between actual adaptation costs and static information-theoretic estimates, we derive a non-linear cost formula that mirrors the Lorentz factor, characterizing a relativistic J-shaped inflation curve -- a "computational wall" that static models are blind to. The validity of these physical principles is examined through a trilogy of decisive experiments: (1) a comparative adjudication of this J-curve inflation against classical Fisher Information models, (2) a geometric analysis of the "Zig-Zag" trajectory of neural architecture evolution, and (3) the implementation of an inertia-aware scheduler wrapper that optimizes the training of deep networks by respecting the agent's physical resistance to change. Our results suggest a unified physical description for the cost of structural adaptation, offering a first-principle explanation for the computational and interpretability-maintenance overhead in intelligent agents.

Jipeng Han

This paper explores the integration of neural networks with logic programming, addressing the longstanding challenges of combining the generalization and learning capabilities of neural networks with the precision of symbolic logic. Traditional attempts at this integration have been hampered by difficulties in initial data acquisition, the reliability of undertrained networks, and the complexity of reusing and augmenting trained models. To overcome these issues, we introduce the COOL (Constraint Object-Oriented Logic) programming language, an innovative approach that seamlessly combines logical reasoning with neural network technologies. COOL is engineered to autonomously handle data collection, mitigating the need for user-supplied initial data. It incorporates user prompts into the coding process to reduce the risks of undertraining and enhances the interaction among models throughout their lifecycle to promote the reuse and augmentation of networks. Furthermore, the foundational principles and algorithms in COOL's design and its compilation system could provide valuable insights for future developments in programming languages and neural network architectures.