IDEAS home Printed from https://ideas.repec.org/a/wsi/jikmxx/v24y2025i01ns0219649225500017.html
   My bibliography  Save this article

Mutual Information-Based Generalisation Gap Analysis Using Deep Learning Model

Author

Listed:
  • Hemanta Kumar Bhuyan

    (Muma College of Business, University of South Florida, 8350 N. Tamiami Trail Sarasota, FL, USA)

  • Bhuvan Unhelkar

    (Muma College of Business, University of South Florida, 8350 N. Tamiami Trail Sarasota, FL, USA)

  • S. Siva Shankar

    (��Department of Computer Science and Engineering, KG Reddy College of Engineering and Technology, Hyderabad, Telangana, India)

  • Prasun Chakrabarti

    (��Department of Computer Science and Engineering, Sir Padampat Singhania University, Udaipur 313601, Rajasthan, India)

Abstract

Most deep learning models face difficulties in analysing image information due to the concept of information bottlenecks and their corresponding methodologies. But, the information bottleneck is used for discarding redundant data and trying to maximise in favour of data directly relevant to the task-oriented information. However, managing information bottlenecks is challenging in the learning model process. Although convolutional neural networks are designed for small-scale processing, their inductive bias makes it difficult to learn contextual features. Thus, we have considered the theoretical learning model to justify the advantages of information bottleneck in deep learning model. We tried to use a fundamental information bottleneck in the vision transformer model. The channel density module cleans up task-related data, while the collected image representations are encouraged to be diverse through local connections in cumulative local transformer blocks. We considered the encoder and decoder methods that analyse the information bottleneck techniques in the deep learning model. This paper presents a rigorous learning theory that mathematically links information bottlenecks for generalisation errors, demonstrating the usefulness of information bottlenecks in deep learning. Our approach suggests that limiting information bottlenecks is crucial for managing errors in deep learning techniques. We conducted experiments across various mathematical models and learning environments to test the validity of our new mathematical insights. In many cases, generalisation errors correspond to unwanted information at hidden levels. We have considered boundary approaches using various scaling parameters and dimensions for the degree of information bottleneck. As per the estimation loss and error by different correlation approaches using generalisation gap methods, we found Spearman correlation having loss (0.86) and error (0.758), whereas Pearson correlation having loss (0.85) and error (0.76), respectively. We also considered outputs for model compression metrics and analysed them through comparative performance.

Suggested Citation

  • Hemanta Kumar Bhuyan & Bhuvan Unhelkar & S. Siva Shankar & Prasun Chakrabarti, 2025. "Mutual Information-Based Generalisation Gap Analysis Using Deep Learning Model," Journal of Information & Knowledge Management (JIKM), World Scientific Publishing Co. Pte. Ltd., vol. 24(01), pages 1-31, February.
  • Handle: RePEc:wsi:jikmxx:v:24:y:2025:i:01:n:s0219649225500017
    DOI: 10.1142/S0219649225500017
    as

    Download full text from publisher

    File URL: http://www.worldscientific.com/doi/abs/10.1142/S0219649225500017
    Download Restriction: Access to full text is restricted to subscribers

    File URL: https://libkey.io/10.1142/S0219649225500017?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:wsi:jikmxx:v:24:y:2025:i:01:n:s0219649225500017. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Tai Tone Lim (email available below). General contact details of provider: http://www.worldscinet.com/jikm/jikm.shtml .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.