Search alternatives:
algorithm relu » algorithm review (Expand Search)
preference » preferences (Expand Search), reference (Expand Search), references (Expand Search)
Showing 1 - 4 results of 4 for search '(( algorithm preference function ) OR ( algorithm relu function ))', query time: 0.06s Refine Results
  1. 1
    Evolution Of Activation Functions for Neural Architecture Search

    Evolution Of Activation Functions for Neural Architecture Search by Nader, Andrew

    Published 2020
    “…However, to the best of our knowledge, the design of new activation functions has mostly been done by hand. In this work, we propose the use of a self-adaptive evolutionary algorithm that searches for new activation functions using a genetic programming approach, and we compare the performance of the obtained activation functions to ReLU. …”
    Get full text
    Get full text
    Get full text
    masterThesis
    Save to List
    Saved in:
  2. 2
    R-CONV++: uncovering privacy vulnerabilities through analytical gradient inversion attacks

    R-CONV++: uncovering privacy vulnerabilities through analytical gradient inversion attacks by Tamer Ahmed Eltaras (22565414)

    Published 2025
    “…The first algorithm presents a novel data leakage method that efficiently exploits convolutional layer gradients, demonstrating that even with non-fully invertible activation functions, such as ReLU, training samples can be analytically reconstructed directly from gradients without the need to reconstruct intermediate layer outputs. …”
    Save to List
    Saved in:
  3. 3
    Intelligent Bilateral Client Selection in Federated Learning Using Game Theory

    Intelligent Bilateral Client Selection in Federated Learning Using Game Theory by Wehbi, Osama

    Published 2022
    “…Our solution involves designing (1) preference functions for the client IoT devices and federated servers to allow them to rank each other according to several factors such as accuracy and price, (2) intelligent matching algorithms that take into account the preferences of both parties in their design, and (3) bootstrapping technique that capitalizes on the collaboration of multiple federated servers in order to assign initial accuracy value for the new connected IoT devices. …”
    Get full text
    Get full text
    Get full text
    masterThesis
    Save to List
    Saved in:
  4. 4
    FoGMatch

    FoGMatch by Arisdakessian, Sarhad

    Published 2019
    “…Our solution consists of (1) two optimization problems, one for the IoT devices and one for the fog nodes, (2) preference functions for both the IoT and fog layers to help them rank each other on the basis of several criteria such latency and resource utilization, and (3) centralized and distributed intelligent scheduling algorithms that consider the preferences of both the fog and IoT layers to improve the performance of the overall IoT ecosystem. …”
    Get full text
    Get full text
    Get full text
    masterThesis
    Save to List
    Saved in:

Search Tools: