IDEAS home Printed from https://ideas.repec.org/a/eee/phsmap/v615y2023ics0378437123001401.html
   My bibliography  Save this article

Structure and performance of fully connected neural networks: Emerging complex network properties

Author

Listed:
  • Scabini, Leonardo F.S.
  • Bruno, Odemir M.

Abstract

Understanding the behavior of Artificial Neural Networks is one of the main topics in the field recently, as black-box approaches have become usual since the widespread of deep learning. Such high-dimensional models may manifest instabilities and weird properties that resemble complex systems. Therefore, we propose Complex Network (CN) techniques to analyze the structure and performance of fully connected neural networks. For that, we build a dataset with 4 thousand models (varying the initialization seed) and their respective CN properties. This is the first work to explore the CN properties of an ample number of fully connected networks accounting for the variance caused by random weight initialization. The networks are trained in a supervised classification setup considering four vision benchmarks and then approached as a weighted and undirected graph of neurons and synapses (learned weights). Results show that neuronal centrality is highly correlated to network classification performance. We also propose the concept of Bag-Of-Neurons (BoN), a CN-based approach for finding topological signatures linking similar neurons. Results suggest that six neuronal types emerge in such networks, independently of the target domain, and are distributed differently according to classification accuracy. We also tackle specific CN properties related to performance, such as higher subgraph centrality on lower-performing models. Our findings suggest that CN properties play a critical role in the performance of fully connected neural networks, with topological patterns emerging independently on a wide range of models.

Suggested Citation

  • Scabini, Leonardo F.S. & Bruno, Odemir M., 2023. "Structure and performance of fully connected neural networks: Emerging complex network properties," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 615(C).
  • Handle: RePEc:eee:phsmap:v:615:y:2023:i:c:s0378437123001401
    DOI: 10.1016/j.physa.2023.128585
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0378437123001401
    Download Restriction: Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

    File URL: https://libkey.io/10.1016/j.physa.2023.128585?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.

    References listed on IDEAS

    as
    1. Erkaymaz, Okan & Ozer, Mahmut, 2016. "Impact of small-world network topology on the conventional artificial neural network for the diagnosis of diabetes," Chaos, Solitons & Fractals, Elsevier, vol. 83(C), pages 178-185.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. He, Haoming & Xiao, Min & Lu, Yunxiang & Wang, Zhen & Tao, Binbin, 2023. "Control of tipping in a small-world network model via a novel dynamic delayed feedback scheme," Chaos, Solitons & Fractals, Elsevier, vol. 168(C).
    2. Soriano-Sánchez, A.G. & Posadas-Castillo, C., 2018. "Smart pattern to generate small–world networks," Chaos, Solitons & Fractals, Elsevier, vol. 114(C), pages 415-422.
    3. Kaya, Ceren & Erkaymaz, Okan & Ayar, Orhan & Özer, Mahmut, 2018. "Impact of hybrid neural network on the early diagnosis of diabetic retinopathy disease from video-oculography signals," Chaos, Solitons & Fractals, Elsevier, vol. 114(C), pages 164-174.
    4. Matjaž Perc & Mahmut Ozer & Janja Hojnik, 2019. "Social and juristic challenges of artificial intelligence," Palgrave Communications, Palgrave Macmillan, vol. 5(1), pages 1-7, December.

    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:eee:phsmap:v:615:y:2023:i:c:s0378437123001401. 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.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with 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: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/physica-a-statistical-mechpplications/ .

    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.