[Paper Review] Implementing Human-like Intuition Mechanism in Artificial Intelligence

Jitesh Dundas, David Chik|arXiv (Cornell University)|Jun 29, 2011

AI-based Problem Solving and Planning5 references4 citations

TL;DR

This paper proposes a connectivity-based intuition model in AI that simulates human-like intuition by handling unknown entities and contextual diversions. Using Poker and car evaluation datasets, it shows that intuition models enhance performance under time and computational constraints but cannot replace logic-based systems, instead serving as supportive aids in complex decision-making scenarios.

ABSTRACT

Human intuition has been simulated by several research projects using artificial intelligence techniques. Most of these algorithms or models lack the ability to handle complications or diversions. Moreover, they also do not explain the factors influencing intuition and the accuracy of the results from this process. In this paper, we present a simple series based model for implementation of human-like intuition using the principles of connectivity and unknown entities. By using Poker hand datasets and Car evaluation datasets, we compare the performance of some well-known models with our intuition model. The aim of the experiment was to predict the maximum accurate answers using intuition based models. We found that the presence of unknown entities, diversion from the current problem scenario, and identifying weakness without the normal logic based execution, greatly affects the reliability of the answers. Generally, the intuition based models cannot be a substitute for the logic based mechanisms in handling such problems. The intuition can only act as a support for an ongoing logic based model that processes all the steps in a sequential manner. However, when time and computational cost are very strict constraints, this intuition based model becomes extremely important and useful, because it can give a reasonably good performance. Factors affecting intuition are analyzed and interpreted through our model.

Motivation & Objective

• To develop an AI model that emulates human-like intuition by incorporating connectivity and unknown entity handling.
• To investigate how diversions and unknown factors affect intuitive decision-making in AI systems.
• To evaluate the reliability and accuracy of intuition-based models compared to traditional logic-based approaches.
• To determine the conditions under which intuition-based models outperform or complement logic-based systems.
• To analyze factors influencing intuition in AI, such as context shifts and non-logical reasoning pathways.

Proposed method

• The model uses a series-based architecture grounded in principles of connectivity and unknown entity integration.
• It processes input data through a non-sequential, associative pathway that mimics intuitive reasoning rather than step-by-step logic.
• The model is trained and evaluated on two benchmark datasets: Poker hand classification and car evaluation.
• Performance is measured by the accuracy of predictions under conditions of ambiguity, missing data, or contextual deviation.
• The model's output is compared against established logic-based models to assess its reliability and utility.
• Factors affecting intuition—such as unexpected inputs and contextual shifts—are systematically analyzed through simulation and evaluation.

Experimental results

Research questions

• RQ1 How can human-like intuition be effectively modeled in artificial intelligence using connectivity and unknown entity handling?
• RQ2 To what extent does the presence of unknown entities or contextual diversions affect the reliability of intuitive AI decisions?
• RQ3 In what scenarios does an intuition-based model outperform or complement logic-based AI systems?
• RQ4 What factors influence the accuracy and consistency of intuitive reasoning in AI, and how can they be quantified?
• RQ5 Can intuition-based models serve as a viable alternative or support mechanism under time and computational constraints?

Key findings

• The intuition-based model achieved reasonably high accuracy in predicting outcomes under time and computational constraints, outperforming logic-based models in speed-sensitive scenarios.
• The presence of unknown entities and contextual diversions significantly reduced the reliability of intuitive predictions, highlighting limitations in robustness.
• Intuition models could not substitute for logic-based systems in handling complex, rule-bound problems requiring sequential reasoning.
• The model demonstrated that non-logical, associative reasoning pathways could yield useful approximations when computational resources were limited.
• Factors such as context deviation and lack of logical structure negatively impacted prediction accuracy, underscoring the need for hybrid systems.
• The model's performance was most effective when used as a supporting mechanism to logic-based models, particularly in dynamic or uncertain environments.