Fractal AI: A fragile theory of intelligence

Cerezo, Sergio Hernandez; Ballester, Guillem Duran

doi:10.48550/arxiv.1803.05049

Cited by 2 publications

(28 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future state maximization embodies a common principle found in multiple, rather novel, research items [30][31][32]34]. To the best of our knowledge, no comparison exists of the various implementations published to date: however, all of them exhibit somewhat intelligent agents [33].…”

Section: Methodsmentioning

confidence: 99%

“…A similar approach to CEF was taken by [31], who were more focused on the computational part, in what they introduced as fractal-AI. Somewhat earlier, [38] pioneered the idea of CEF with their empowerment prospect: herein, an agent, rather than maximizing the entropy of its state, aimed at maximizing its control over said state [38].…”

Section: Literature Reviewmentioning

confidence: 99%

“…The behavior of systems ranging from cosmological [28] to biological domains [29] has recently been described using a single, fundamental, entropy-based formalism [30]: similar advances in AI research have incorporated this mechanism as an approach to approximating intelligence in known environments [30][31][32]. These methods have been summarized under the term "future state maximization" (FSX) [33].…”

Section: Introductionmentioning

confidence: 99%

“…Research on FSX has mostly explored the astonishing cooperation emerging among swarms of agents equipped with such decision mechanics [30][31][32]34]. Behavior in ABM, however, should be capable of depicting interaction beyond beneficial effects for all enti-ties [35,36].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Applicability of the Future State Maximization Paradigm to Agent-Based Modeling: A Case Study on the Emergence of Socially Sub-Optimal Mobility Behavior

Plakolb

Strelkovskii

2023

Systems

View full text Add to dashboard Cite

Novel developments in artificial intelligence excel in regard to the abilities of rule-based agent-based models (ABMs), but are still limited in their representation of bounded rationality. The future state maximization (FSX) paradigm presents a promising methodology for describing the intelligent behavior of agents. FSX agents explore their future state space using “walkers” as virtual entities probing for a maximization of possible states. Recent studies have demonstrated the applicability of FSX to modeling the cooperative behavior of individuals. Applied to ABMs, the FSX principle should also represent non-cooperative behavior: for example, in microscopic traffic modeling, there is a need to model agents that do not fully adhere to the traffic rules. To examine non-cooperative behavior arising from FSX, we developed a road section model populated by agent-cars endowed with an augmented FSX decision making algorithm. Simulation experiments were conducted in four scenarios modeling various traffic settings. A sensitivity analysis showed that cooperation among the agents was the result of a balance between exploration and exploitation. We showed that our model reproduced several patterns observed in rule-based traffic models. We also demonstrated that agents acting according to FSX can stop cooperating. We concluded that FSX can be useful for studying irrational behavior in certain traffic settings, and that it is suitable for ABMs in general.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Applicability of the Future State Maximization Paradigm to Agent-Based Modeling: A Case Study on the Emergence of Socially Sub-Optimal Mobility Behavior

Plakolb

Strelkovskii

2023

Systems

View full text Add to dashboard Cite

show abstract

“…The second law of thermodynamics is a fundamental law of physics. Entropy maximization might be a general phenomenon in physics, cosmology, computer science, and animal behavior [8][9][10]. Recent works also associated entropy maximization with the intellectual ability to increase future freedom of action [8,11,12].…”

Section: Holographic Considerations (The Field Representation Of Comp...mentioning

confidence: 99%

Will Artificial Intelligence Become Conscious? Can Thermodynamics Explain the Evolution of Intellect?

2022

JMTCM

View full text Add to dashboard Cite

Deep neural networks (DNNs), founded on the brain's neuronal organization, can extract higher-level features from raw input. However, complex intellect via autonomous decision-making is way beyond current AI design. Here we propose an autonomous AI inspired by the thermodynamic cycle of sensory perception, operating between two information density reservoirs. Stimulus unbalances the high entropy resting-state and triggers a thermodynamic cycle. By recovering the initial conditions, self-regulation generates a response while accumulating an orthogonal, holographic potential. The resulting high-density manifold is a stable memory and experience field, which increases future freedom of action via intelligent decision-making

show abstract

Fractal AI: A fragile theory of intelligence

Cited by 2 publications

References 0 publications

Applicability of the Future State Maximization Paradigm to Agent-Based Modeling: A Case Study on the Emergence of Socially Sub-Optimal Mobility Behavior

Applicability of the Future State Maximization Paradigm to Agent-Based Modeling: A Case Study on the Emergence of Socially Sub-Optimal Mobility Behavior

Will Artificial Intelligence Become Conscious? Can Thermodynamics Explain the Evolution of Intellect?

Contact Info

Product

Resources

About