The Evolutionary Buffet Method

Hintze, Arend; Schossau, Jory; Bohm, Clifford

doi:10.1007/978-3-030-04735-1_2

Cited by 10 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evolution is more than a route to the optimal solution, and has a wide range of idiosyncracies that can have an impact on the development of cognitive abilities. These idiosyncracies are core components of biological systems: the way mutations alter strategies confounds the trajectory of optimization (Adami et al, 2016;Schossau & Hintze, 2020); the computational (biological) substrate used to implement cognitive mechanisms profoundly confounds any evolved solutions (Hintze et al, 2019); and the number of environmental parameters that could guide evolution are innumerable. This complex interdependent nature of cognitive evolution superficially appears as a barrier to psychological inquiry, yet the careful and controlled investigation of conditions that lead to the emergence of different decision strategies is the strength of this approach.…”

Section: Understanding Cognitive Evolutionmentioning

confidence: 99%

Using artificial intelligence to fit, compare, evaluate, and discover computational models of decision behavior

Kvam¹,

Sokratous²,

Fitch³

et al. 2023

Preprint

View full text Add to dashboard Cite

Theories of decision making are implemented in models that predict and explain behavior in terms of latent cognitive processes. But where do these models come from, and how are they instantiated in the brain? In this paper, we examine several avenues where artificial intelligence (AI) and machine learning (ML) can benefit decision theory by providing new methods for developing and testing cognitive models. First, machine learning can be used to efficiently estimate the values of latent parameters in cognitive models, and assign posterior probabilities to competing models of the same observed data. Second, models of decision behavior can be embedded within artificially intelligent systems to allow them to make inferences about human counterparts (goals, abilities, cognition) in real time, equipping AI better tools to interact socially. Third, AI can be used to understand how evolutionary and learning processes give rise to the cognitive abilities that support decision-making. Finally, the tools of experimental psychology and decision sciences can be applied to better understand the ``black boxes'' of neural networks by systematically testing input-output (stimulus-response) relationships. Put together, we suggest that merging ML/AI into decision modeling -- and vice versa -- is a promising path toward many long-term benefits for both fields.

show abstract

Section: Understanding Cognitive Evolutionmentioning

confidence: 99%

Using artificial intelligence to fit, compare, evaluate, and discover computational models of decision behavior

Kvam¹,

Sokratous²,

Fitch³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…At every generation in the evolution optimization, agents were evaluated within their task environment. In this study, MBs were trained to solve a spatial navigation task, MABE's "PathFollow" world, which was first described in [15] as an associative memory task (see also https://github.com/Hintzelab/MABE/tree/feature-path_follow_world/ code/World/PathFollowWorld, accessed on 15 September 2021). In this task, the agent is rewarded for each location visited along a predefined path, with 45 • turns indicated by left and right turn symbols (Figure 1B).…”

Section: "Pathfollow" Environmentmentioning

confidence: 99%

“…For this reason, and because qualitatively different network architectures excel in distinct task domains, comparisons between different types of networks performing the same tasks are rare. One exception is recent work by Hintze et al [103], who compared the evolved representation (R) and its "smeardness" across hidden units in MBs and rANNs performing the same active perceptual categorization task (see also [15]).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Quantifying the Autonomy of Structurally Diverse Automata: A Comparison of Candidate Measures

Albantakis

2021

Entropy

View full text Add to dashboard Cite

Should the internal structure of a system matter when it comes to autonomy? While there is still no consensus on a rigorous, quantifiable definition of autonomy, multiple candidate measures and related quantities have been proposed across various disciplines, including graph-theory, information-theory, and complex system science. Here, I review and compare a range of measures related to autonomy and intelligent behavior. To that end, I analyzed the structural, information-theoretical, causal, and dynamical properties of simple artificial agents evolved to solve a spatial navigation task, with or without a need for associative memory. By contrast to standard artificial neural networks with fixed architectures and node functions, here, independent evolution simulations produced successful agents with diverse neural architectures and functions. This makes it possible to distinguish quantities that characterize task demands and input-output behavior, from those that capture intrinsic differences between substrates, which may help to determine more stringent requisites for autonomous behavior and the means to measure it.

show abstract

“…Some work, particularly in algorithm optimization, has dealt with combining components of multiple structures to create efficient computational hybrids. One such technique is the "Buffet Method", which allows a computational structure to access an array of different types of information processing sub-structures during the evolutionary process (Hintze et al, 2019) and shows that the proportion of sub-structures used in the evolved solutions is task dependent. Another method known as "Auto ML" is designed to evolve a substrate from basic mathematical principles (Real et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

The Comparative Hybrid Approach to Investigate Cognition across Substrates

Albani¹,

Ackles²,

Ofria³

et al. 2021

The 2021 Conference on Artificial Life

Self Cite

View full text Add to dashboard Cite

Understanding the structure and evolution of cognition is a topic of broad scientific interest. Computational substrates are ideal for conducting investigations into this topic because they can be incorporated in rapidly evolving Artificial Life systems and are easy to manipulate. However, design differences between currently existing digital systems make it difficult to identify which manipulations are responsible for broad patterns in evolved behavior. This is further confounded if we are trying to disentangle how multiple features interact. Here we systematically analyze components from two evolvable digital neural substrates (Recurrent Artificial Neural Networks (RNNs) and Markov brains) to develop a proofof-concept for a comparative hybrid approach. We identified elements of the logic and memory storage architectures in each substrate, then altered and recombined properties of the original substrates to create hybrid substrates. In particular, we chose to investigate the differences between RNNs and Markov Brains relating to network sparsity, whether memory is discrete or continuous, and the basic logic operator in each substrate. We then tested the original substrates and the hybrids across a suite of distinct environments with different logic and memory requirements. While we observed trends across all three of the axes that we investigated, we identified discreteness of memory as an especially important determinant of performance across our test conditions. However, the specific effect of discretization varied by environment and whether the associated task relied on information integration. Our results demonstrate that the comparative hybrid approach can identify structural components that enable cognition and facilitate task performance across multiple computational structures.

show abstract

The Evolutionary Buffet Method

Cited by 10 publications

References 25 publications

Using artificial intelligence to fit, compare, evaluate, and discover computational models of decision behavior

Using artificial intelligence to fit, compare, evaluate, and discover computational models of decision behavior

Quantifying the Autonomy of Structurally Diverse Automata: A Comparison of Candidate Measures

The Comparative Hybrid Approach to Investigate Cognition across Substrates

Contact Info

Product

Resources

About