Wyniki wyszukiwania - BazTech

1

On Loss Functions for Deep Neural Networks in Classification

Janocha K., Czarnecki W. M.

Schedae Informaticae

|

2016

|

Vol. 25

49--59

EN

Deep neural networks are currently among the most commonly used classifiers. Despite easily achieving very good performance, one of the best selling points of these models is their modular design – one can conveniently adapt their architecture to specific needs, change connectivity patterns, attach specialised layers, experiment with a large amount of activation functions, normalisation schemes and many others. While one can find impressively wide spread of various configurations of almost every aspect of the deep nets, one element is, in authors’ opinion, underrepresented – while solving classification problems, vast majority of papers and applications simply use log loss. In this paper we try to investigate how particular choices of loss functions affect deep models and their learning dynamics, as well as resulting classifiers robustness to various effects. We perform experiments on classical datasets, as well as provide some additional, theoretical insights into the problem. In particular we show that L1 and L2 losses are, quite surprisingly, justified classification objectives for deep nets, by providing probabilistic interpretation in terms of expected misclassification. We also introduce two losses which are not typically used as deep nets objectives and show that they are viable alternatives to the existing ones.

2

On the Consistency of Multithreshold Entropy Linear Classifier

Czarnecki W. M.

Schedae Informaticae

|

2015

|

Vol. 24

123--132

EN

Multithreshold Entropy Linear Classifier (MELC) is a recent classifier idea which employs information theoretic concept in order to create a multithreshold maximum margin model. In this paper we analyze its consistency over multithreshold linear models and show that its objective function upper bounds the amount of misclassified points in a similar manner like hinge loss does in support vector machines. For further confirmation we also conduct some numerical experiments on five datasets.

3

Zarządzanie zasobami w harmonogramowaniu wieloobiektowych przedsięwzięć budowlanych z wykorzystaniem teorii szeregowania zadań

Podolski M.

Przegląd Budowlany

|

2014

|

R. 85, nr 4

42--47

PL

W artykule przedstawiono problematykę możliwości optymalnego zarządzania zasobami realizatora w wieloobiektowym przedsięwzięciu budowlanym. Podczas planowania tego rodzaju przedsięwzięć można wykorzystać pojęcia i narzędzia stosowane w teorii szeregowania zadań. W trakcie tworzenia dla nich harmonogramów mogą być stosowane współcześnie dostępne techniki, które pozwalają na znaczące skrócenie czasu realizacji przedsięwzięcia. Do rozwiązywania zadania optymalizacyjnego zastosowano metaheurystyczny algorytm poszukiwania z zakazami (tabu search) stosowany w teorii szeregowania zadań. W artykule zaprezentowano przykład obliczeniowy dla omawianego zagadnienia.

EN

The article presents the problem of optimal possibilities in managing resources of the executor of a multi-object construction project. During the planning of such projects the concepts and tools used in the classification theory may be applied. While creating the schedules, available modern techniques that allow for a significant reduction of the execution time of a project may be applied. To solve the optimization task, the metaheuristic search algorithm with prohibitions (tabu search) applied in the task classification theory was used. A computational example of the problem in question is presented in the article.