On Heuristic Models, Assumptions, and Parameters

• URL: http://arxiv.org/abs/2201.07413v3
• Date: Wed, 28 May 2025 13:31:02 GMT
• Title: On Heuristic Models, Assumptions, and Parameters
• Authors: Samuel Judson, Joan Feigenbaum,
• Abstract summary: We argue that there is an underappreciated family of obscure and opaque technical caveats, choices, and qualifiers.<n>We describe three specific classes of such objects: models, assumptions, and parameters.
• Score: 0.6445605125467574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Insightful interdisciplinary collaboration is essential to the principled governance of technology. When such efforts address the interaction between computation and society, they often focus on modeling, the process by which computer scientists formally define problems in order to enable algorithmic solutions. But modeling is a multifaceted and inherently imperfect process. Especially in interdisciplinary work, it often receives uneven scrutiny because of the practical challenges of communicating complex technical details to non-experts. We argue that there is an underappreciated if loose family of obscure and opaque technical caveats, choices, and qualifiers that the social effects of computing can depend just as much on as far more heavily scrutinized modeling choices. These artifacts are often used by researchers to paper over the incomplete theoretical foundations of computing or to burden shift responsibility for the impact of normative design decisions. Further, their nuanced technical nature often complicates thorough sociotechnical scrutiny of the discretionary decisions made to manage them. We describe three specific classes of such objects: heuristic models, assumptions, and parameters. We raise six reasons these objects may be hazardous to comprehensive analysis of computing and argue they deserve deliberate consideration as researchers explain scientific work.

Related papers

• Tinkering Against Scaling [15.060264126253212]
  We propose a "tinkering" approach that is inspired by existing works. This method involves engaging with smaller models or components that are manageable for ordinary researchers. We argue that tinkering is both a way of making and knowing for computational social science and a way of knowing for critical studies.
  arXiv  Detail & Related papers  (2025-04-23T09:21:39Z)
• Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1) [66.51642638034822]
  Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks.<n>Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic domains.<n>This paper offers a concise yet insightful overview of reasoning techniques in both textual and multimodal LLMs.
  arXiv  Detail & Related papers  (2025-04-04T04:04:56Z)
• A Survey on State-of-the-art Deep Learning Applications and Challenges [0.0]
  Building a deep learning model is challenging due to the algorithm's complexity and the dynamic nature of real-world problems. This study aims to comprehensively review the state-of-the-art deep learning models in computer vision, natural language processing, time series analysis and pervasive computing.
  arXiv  Detail & Related papers  (2024-03-26T10:10:53Z)
• A Review of Neuroscience-Inspired Machine Learning [58.72729525961739]
  Bio-plausible credit assignment is compatible with practically any learning condition and is energy-efficient. In this paper, we survey several vital algorithms that model bio-plausible rules of credit assignment in artificial neural networks. We conclude by discussing the future challenges that will need to be addressed in order to make such algorithms more useful in practical applications.
  arXiv  Detail & Related papers  (2024-02-16T18:05:09Z)
• Designing Explainable Predictive Machine Learning Artifacts: Methodology and Practical Demonstration [0.0]
  Decision-makers from companies across various industries are still largely reluctant to employ applications based on modern machine learning algorithms. We ascribe this issue to the widely held view on advanced machine learning algorithms as "black boxes" We develop a methodology which unifies methodological knowledge from design science research and predictive analytics with state-of-the-art approaches to explainable artificial intelligence.
  arXiv  Detail & Related papers  (2023-06-20T15:11:26Z)
• Alternative models: Critical examination of disability definitions in the development of artificial intelligence technologies [6.9884176767901005]
  This article presents a framework for critically examining AI data analytics technologies through a disability lens. We consider three conceptual models of disability: the medical model, the social model, and the relational model. We show how AI technologies designed under each of these models differ so significantly as to be incompatible with and contradictory to one another.
  arXiv  Detail & Related papers  (2022-06-16T16:41:23Z)
• Ising machines as hardware solvers of combinatorial optimization problems [1.8732539895890135]
  Ising machines are hardware solvers which aim to find the absolute or approximate ground states of the Ising model. A scalable Ising machine that outperforms existing standard digital computers could have a huge impact for practical applications.
  arXiv  Detail & Related papers  (2022-04-01T08:24:06Z)
• Simulation Intelligence: Towards a New Generation of Scientific Methods [81.75565391122751]
  "Nine Motifs of Simulation Intelligence" is a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence. We argue the motifs of simulation intelligence are interconnected and interdependent, much like the components within the layers of an operating system. We believe coordinated efforts between motifs offers immense opportunity to accelerate scientific discovery.
  arXiv  Detail & Related papers  (2021-12-06T18:45:31Z)
• Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation [52.903665881174845]
  We propose a pyramid of types of knowledge required in computational argumentation. We briefly discuss the state of the art on the role and integration of these types in the field.
  arXiv  Detail & Related papers  (2021-07-01T08:12:41Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)
• Individual Explanations in Machine Learning Models: A Case Study on Poverty Estimation [63.18666008322476]
  Machine learning methods are being increasingly applied in sensitive societal contexts. The present case study has two main objectives. First, to expose these challenges and how they affect the use of relevant and novel explanations methods. And second, to present a set of strategies that mitigate such challenges, as faced when implementing explanation methods in a relevant application domain.
  arXiv  Detail & Related papers  (2021-04-09T01:54:58Z)
• Individual Explanations in Machine Learning Models: A Survey for Practitioners [69.02688684221265]
  The use of sophisticated statistical models that influence decisions in domains of high societal relevance is on the rise. Many governments, institutions, and companies are reluctant to their adoption as their output is often difficult to explain in human-interpretable ways. Recently, the academic literature has proposed a substantial amount of methods for providing interpretable explanations to machine learning models.
  arXiv  Detail & Related papers  (2021-04-09T01:46:34Z)
• Learning-Driven Decision Mechanisms in Physical Layer: Facts, Challenges, and Remedies [23.446736654473753]
  This paper introduces the common assumptions in the physical layer to highlight their discrepancies with practical systems. As a solution, learning algorithms are examined by considering implementation steps and challenges.
  arXiv  Detail & Related papers  (2021-02-14T22:26:44Z)
• Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning [69.99522650448213]
  Research in machine learning is at a turning point. Research interests are shifting away from increasing the performance of highly parameterized models to exceedingly specific tasks. This white paper provides an introduction and discussion of this emerging field in machine learning research.
  arXiv  Detail & Related papers  (2020-12-21T15:07:19Z)
• Qualities, challenges and future of genetic algorithms: a literature review [0.0]
  Genetic algorithms are computer programs that simulate natural evolution. They have been used to solve various optimisation problems from neural network architecture search to strategic games. Recent developments such as GPU, parallel and quantum computing, conception of powerful parameter control methods, and novel approaches in representation strategies may be keys to overcome their limitations.
  arXiv  Detail & Related papers  (2020-11-05T17:53:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.