National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Evolutionary Design of Non-Linear Functions for Convolutional Neural Networks
Hladiš, Martin ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
The aim of this thesis is to design and implement a program for automated design of nonlinear activation functions for convolutional neural networks (CNN) using evolutionary algorithms. The use of automated design provides an independent view to systematically explore a wide range of activation functions and identify the best ones. The method for automatic design chosen in this thesis is a form of evolutionary algorithms referred to as Cartesian genetic programming, which uses a graph representation to encode the solution. This technique allows for the definition of a set of mathematical primitives that define the search space, and thus simply parameterize the design. The implemented approach has been tested on several different architectures and datasets (LeNet-5 \& MNIST, ResNet-10 \& FashionMNIST, WRN-40-4 \& CIFAR-10). Experiments have shown that the approach can find activation functions that statistically improve the accuracy of the architecture over the commonly used ReLU function.
Učení vícevrstvých perceptronů s po částech lineárními aktivačními funkcemi
Kozub, P. ; Holeňa, Martin
This paper presents an overview of the techniques used to solve constrained optimization problems using evolutionary algorithms. The construction of the fitness function together with the handling of feasible and infeasible individuals is discussed. Approaches using penalty functions, special representations, repair algorithms, methods based on separation of objective and constraints and multiobjective techniques are mentioned.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.