Search Results - "Ceberio, Martine"

Refine Results
  1. 1

    Why Dilated Convolutional Neural Networks: A Proof of Their Optimality by Contreras, Jonatan, Ceberio, Martine, Kreinovich, Vladik

    Published in Entropy (Basel, Switzerland) (18-06-2021)
    “…One of the most effective image processing techniques is the use of convolutional neural networks that use convolutional layers. In each such layer, the value…”
    Get full text
    Journal Article
  2. 2

    When is deep learning better and when is shallow learning better: qualitative analysis by Robles Herrera, Salvador, Ceberio, Martine, Kreinovich, Vladik

    “…In many practical situations, deep neural networks work better than the traditional 'shallow' ones; however, in some cases, the shallow neural networks lead to…”
    Get full text
    Journal Article
  3. 3

    Let Us Use Negative Examples in Regression-Type Problems Too by Contretas, Jonatan, Zapata, Francisco, Kosheleva, Olga, Kreinovich, Vladik, Ceberio, Martine

    “…In many practical situations, we need to reconstruct the dependence between quantities x and y based on several situations in which we know both x and y…”
    Get full text
    Conference Proceeding
  4. 4

    Between Dog and Wolf: A Continuous Transition from Fuzzy to Probabilistic Estimates by Ceberio, Martine, Kosheleva, Olga, Kreinovich, Vladik, Longpre, Luc

    “…Often, we use original expert estimates to compute estimates of related quantities. In many practical situations, it is desirable to know how accurate is the…”
    Get full text
    Conference Proceeding
  5. 5

    In Its Usual Formulation, Fuzzy Computation Is, In General, NP-Hard, But a More Realistic Formulation Can Make It Feasible by Ceberio, Martine, Kosheleva, Olga, Kreinovich, Vladik, Longpre, Luc

    “…In many practical situations, we cannot directly measure or estimate the desired quantity y - e.g., we cannot directly measure the distance to a star or the…”
    Get full text
    Conference Proceeding
  6. 6

    Efficient interval partitioning—Local search collaboration for constraint satisfaction by Pedamallu, Chandra Sekhar, Ozdamar, Linet, Ceberio, Martine

    Published in Computers & operations research (01-05-2008)
    “…In this article, a cooperative solution methodology that integrates interval partitioning ( IP) algorithms with a local search, feasible sequential quadratic…”
    Get full text
    Journal Article
  7. 7
  8. 8

    Latinas' resilience and persistence in computer science and engineering: Preliminary findings of a qualitative study examining identity and agency by Esquinca, Alberto, Villa, Elsa Q., Hampton, Elaine, Ceberio, Martine, Wandermurem, Luciene

    “…Most professions have reached gender equity with the exception of computer science and engineering. To understand the mitigating factors influencing Latinas'…”
    Get full text
    Conference Proceeding Journal Article
  9. 9

    Why Fuzzy Control Is Often More Robust (and Smoother): A Theoretical Explanation by Csiszar, Orsolya, Csiszar, Gabor, Kosheleva, Olga, Ceberio, Martine, Kreinovich, Vladik

    “…In many practical situations, practitioners use easier-to-compute fuzzy control to approximate the more-difficult-to-compute optimal control. As expected, for…”
    Get full text
    Conference Proceeding
  10. 10

    Towards adding probabilities and correlations to interval computations by Berleant, Daniel, Ceberio, Martine, Xiang, Gang, Kreinovich, Vladik

    “…The paper is a continuation of our previous work towards the use of probability information in interval computations. While in the previous work, bounds on the…”
    Get full text
    Journal Article
  11. 11

    Which Activation Function Works Best for Training Artificial Pancreas: Empirical Fact and Its Theoretical Explanation by Denes-Fazakas, Lehel, Szilagyi, Laszlo, Eigner, Gyorgy, Kosheleva, Olga, Ceberio, Martine, Kreinovich, Vladik

    “…One of the most effective ways to help patients at the dangerous levels of diabetes is an artificial pancreas, a device that constantly monitors the patient's…”
    Get full text
    Conference Proceeding
  12. 12

    How to Use Quantum Computing to Check Which Inputs Are Relevant: A Proof That Deutsch-Jozsa Algorithm Is, In Effect, the Only Possibility by Kreinovich, Vladik, Ceberio, Martine, Alvarez, Ricardo

    “…One of the main reasons why computations - in particular, engineering computations - take long is that, to be on the safe side, models take into account all…”
    Get full text
    Conference Proceeding
  13. 13

    Using Interval Constraint Solving Techniques to better understand and predict future behaviors of dynamic problems by Valera, Leobardo, Ceberio, Martine

    “…The ability to make observations of natural phenomena has played a fundamental role in our world. From what we observe, models are derived and we can get an…”
    Get full text
    Conference Proceeding
  14. 14

    Greetings from NAFIPS 2016 organizing committee chairs by Ceberio, Martine, Kreinovich, Vladik

    “…Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the…”
    Get full text
    Conference Proceeding
  15. 15

    Processing interval sensor data in the presence of outliers, with potential applications to localizing underwater robots by Sliwka, J., Jaulin, L., Ceberio, M., Kreinovich, V.

    “…Measurements are never absolutely accurate, the measurement result x̃ is, in general, different from the actual (unknown) values x of the corresponding…”
    Get full text
    Conference Proceeding
  16. 16

    Faster Quantum Alternative to Softmax Selection in Deep Learning and Deep Reinforcement Learning by Galindo, Oscar, Ayub, Christian, Ceberio, Martine, Kreinovich, Vladik

    “…Deep learning and deep reinforcement learning are, at present, the best available machine learning tools for use in engineering problems. However, at present,…”
    Get full text
    Conference Proceeding
  17. 17

    Interval-type and affine arithmetic-type techniques for handling uncertainty in expert systems by Ceberio, Martine, Kreinovich, Vladik, Chopra, Sanjeev, Longpré, Luc, Nguyen, Hung T., Ludäscher, Bertram, Baral, Chitta

    “…Expert knowledge consists of statements S j (facts and rules). The facts and rules are often only true with some probability. For example, if we are interested…”
    Get full text
    Journal Article Conference Proceeding
  18. 18

    Towards predictions of large dynamic systems' behavior using reduced-order modeling and interval computations by Valera, Leobardo, Garcia, Angel, Gholamy, Afshin, Ceberio, Martine, Florez, Horacio

    “…The ability to conduct fast and reliable simulations of dynamic systems is of special interest to many fields of operations. Such simulations can be very…”
    Get full text
    Conference Proceeding
  19. 19

    Message from NAFIPS 2012 program chairs

    “…There are six special sessions-oriented events planned throughout the conference, as well as a student paper session. There will also be a NAFIPS general…”
    Get full text
    Conference Proceeding
  20. 20

    Robust data processing in the presence of uncertainty and outliers: Case of localization problems by Welte, Anthony, Jaulin, Luc, Ceberio, Martine, Kreinovich, Vladik

    “…To properly process data, we need to take into account both the measurement errors and the fact that some of the observations may be outliers. This is…”
    Get full text
    Conference Proceeding