skip to main content
10.1145/3574131.3574444acmconferencesArticle/Chapter ViewAbstractPublication PagessiggraphConference Proceedingsconference-collections
research-article

Computer-vision Classification-algorithms Are Inherently Creative When Error-prone

Published: 13 January 2023 Publication History

Abstract

Whether coming from a linear support vector machine, from logistic regression, or a quasi-Newtonian, the fine-tuning of the decision boundary in any given data set is essential to mitigate the loss term so that neural nets in image recognition can divide a data space into separate sections and correctly classify an input. By their very nature, neural nets are logically non-deterministic but rest on probability-weighted associations, which are adjusted recursively to enhance the similarity of intermediate results to the target output, the remaining difference being the ‘error.’ However, taxonomies should not be crisp but seen as fuzzy classes, allowing for hybrid exemplars that transgress category boundaries. The associative and similarity orientation of neural nets and deep learning makes such systems inherently creative in that misclassifications are at the basis of creative crossovers in information processing. This new conceptualization of network errors is supported by the ratings of 40 top-ranking designers of 20 image-recognition mistakes on the dimensions of creativity and innovativeness.

References

[1]
Claire Cottrell. 2012. Are you going to eat that chair? Yes, and my pencil is cheese, and this candle is chocolate. (November 2012) The Atlantic. Retrieved November 17, 2022 from https://www.theatlantic.com/health/archive/2012/11/are-you-going-to-eat-that-chair-yes-and-my-pencil-is-cheese-and-this-candle-is-chocolate/265629/
[2]
Grape Japan. 2022. Designer's transforming frilled lizard pencil sharpener is just too genius. (October 2022) Grape. Retrieved November 17, 2022 from https://grapee.jp/en/212754
[3]
Pin Wang, En Fan, and Peng Wang. 2021. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognition Letters 141, (2021), 61-67.
[4]
Susmita Ray. 2019. A quick review of machine learning algorithms. In 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon) (pp. 35-39). IEEE.
[5]
Li Yang and Abdallah Shami. 2020. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing 415, (2020), 295-316.
[6]
Pratap C. Sen, Mahimarnab Hajra, and Mitadru Ghosh. 2020. Supervised classification algorithms in machine learning: A survey and review. In Emerging technology in modelling and graphics (pp. 99-111). Springer, Singapore.
[7]
Swathi Pothuganti. 2018. Review on over-fitting and under-fitting problems in Machine Learning and solutions. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering 7, 9 (2018), 3692-3695
[8]
Himabindu Lakkaraju, Ece Kamar, Rich Caruana, and Eric Horvitz. 2017. Identifying unknown unknowns in the open world: Representations and policies for guided exploration. In S. Singh and S. Markovitch (Eds.), Proceedings of the 31st AAAI Conference on Artificial Intelligence, Feb. 4-7, 2017, SF, CA (pp. 2124-2132). Palo Alto, CA: AAAI.
[9]
Sourish Ghosh, Anasuya Dasgupta, and Aleena Swetapadma. 2019. A study on support vector machine based linear and non-linear pattern classification. In 2019 International Conference on Intelligent Sustainable Systems (ICISS) (pp. 24-28). IEEE.
[10]
Jaehyun Yoon. 2021. Forecasting of real GDP growth using machine learning models: gradient boosting and random forest approach. Computational Economics 57, (2021), 247-265.
[11]
Wenyang Wang and Dongchu Sun. 2021. The improved AdaBoost algorithms for imbalanced data classification. Information Sciences 563, (2021), 358-374.
[12]
Rakesh Katuwal, Ponnuthurai N. Suganthan, and Le Zhang. 2020. Heterogeneous oblique random forest. Pattern Recognition 99, (2020), 107078.
[13]
Johan F. Hoorn. 2012. Epistemics of the virtual. Philadelphia, PA: John Benjamins.
[14]
Muchid Mustafa Saritas and Ali Yasar. 2019. Performance analysis of ANN and Naive Bayes classification algorithm for data classification. International Journal of Intelligent Systems and Applications in Engineering 7, 2 (2019), 88-91.
[15]
Chunhui Yuan and Haitao Yang. 2019. Research on K-value selection method of K-means clustering algorithm. J, Multidisciplinary Scientific Journal 2, 2 (2019), 226-235.
[16]
Johan F. Hoorn and Denice J. Tuinhof. 2022. A robot's sense-making of fallacies and rhetorical tropes. Creating ontologies of what humans try to say. Cognitive Systems Research 72, (2022), 116-130.
[17]
Johan F. Hoorn. 2002. A model for information technologies that can be creative. In T. T. Hewett, & T. Kavanagh (Eds.), Proceedings of the Fourth Creativity and Cognition Conference, Loughborough, UK (pp. 186-191). New York: ACM.
[18]
Johan F. Hoorn. 2014. Creative confluence. Philadelphia, PA: John Benjamins.
[19]
Margaret A. Boden. 2004. The creative mind: myths and mechanisms. London: Routledge.
[20]
Margaret A. Boden. 2009. Computer models of creativity. AI Magazine 30, 3 (2009), 23-34.
[21]
Johan F. Hoorn. 2022. Erroneous AI-classification systems produce creative design ideas, predicting level of innovation value. Preprints 2022, 2022060148.
[22]
Alan M. Turing. 1950. I.—Computing machinery and intelligence. Mind, LIX, 236 (1950), 433-460.
[23]
Hutan Ashrafian, Ara Darzi, and Thanos Athanasiou. 2015. A novel modification of the Turing test for artificial intelligence and robotics in healthcare. The International Journal of Medical Robotics and Computer Assisted Surgery 11, (2015), 38-43.
[24]
Edward A. Feigenbaum. 2003. Some challenges and grand challenges for computational intelligence. Journal of the Association for Computing Machinery 50, (2003), 32-40.
[25]
J. Chapman McGrew and Charles B. Monroe. 2000. An introduction to statistical problem solving in geography. Long Grove, IL: Waveland Press.
[26]
Stella Vosniadou and Andrew Ortony. 1989. Similarity and analogical reasoning: a synthesis. In A. Ortony and S. Vosniadou (Eds.), Similarity and analogical reasoning (pp. 1-18), Cambridge, UK: Cambridge University.
[27]
Isabelle Blanchette and Kevin Dunbar. 2000. How analogies are generated: The roles of structural and superficial similarity. Memory and Cognition 28, 1 (2000), 108-124.
[28]
Alzir F. B. Antunes, Christel Lingnau, and Jorge A. S. Centeno. 2003. Object oriented analysis and semantic network for high-resolution image classification. Bulletin of Geodetic Sciences 9, 2 (2003), 233-242.
[29]
Tadahiro Tangiuchi, Daichi Mochihashi, Takayuki Nagai, Satoru Uchida, Naoya Inoue, Ichiro Kobayashi, 2019. Survey on frontiers of language and robotics. Advanced Robotics 33, 15-16 (2019), 700-730.
[30]
Qi Wang, Yue Ma, Kun Zhao, and Yingjie Tian. 2022. A comprehensive survey of loss functions in machine learning. Annals of Data Science 9, (2022), 187-212.

Index Terms

  1. Computer-vision Classification-algorithms Are Inherently Creative When Error-prone

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image ACM Conferences
        VRCAI '22: Proceedings of the 18th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry
        December 2022
        284 pages
        ISBN:9798400700316
        DOI:10.1145/3574131
        • Editors:
        • Enhua Wu,
        • Lionel Ming-Shuan Ni,
        • Zhigeng Pan,
        • Daniel Thalmann,
        • Ping Li,
        • Charlie C.L. Wang,
        • Lei Zhu,
        • Minghao Yang
        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Sponsors

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 13 January 2023

        Permissions

        Request permissions for this article.

        Check for updates

        Author Tags

        1. Computational creativity
        2. Deep learning
        3. Error
        4. Misclassification
        5. Neural networks

        Qualifiers

        • Research-article
        • Research
        • Refereed limited

        Funding Sources

        • Start-up Fund for New Recruits

        Conference

        VRCAI '22
        Sponsor:

        Acceptance Rates

        Overall Acceptance Rate 51 of 107 submissions, 48%

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • 0
          Total Citations
        • 105
          Total Downloads
        • Downloads (Last 12 months)22
        • Downloads (Last 6 weeks)2
        Reflects downloads up to 19 Feb 2025

        Other Metrics

        Citations

        View Options

        Login options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        HTML Format

        View this article in HTML Format.

        HTML Format

        Figures

        Tables

        Media

        Share

        Share

        Share this Publication link

        Share on social media