Dawid Kopczyk - Academia.edu (original) (raw)
Uploads
Papers by Dawid Kopczyk
2019 6th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2019
We present a method for optimizing traffic signal settings which can be used for offline planning... more We present a method for optimizing traffic signal settings which can be used for offline planning and realtime adaptive traffic management. The method is based on metaheuristics efficiently exploring space of possible settings and evaluating candidate solutions using a microscopic traffic simulation or metamodels of simulations built using machine learning algorithms (e.g., neural networks, LightGBM). We present results of extensive experiments and compare different algorithms and their configurations in order to find the best approach in our use case. Experiments were carried out on a realistic road network of Warsaw (maps originated from the OpenStreetMap service) and showed that LightGBM may outperform neural networks in terms of accuracy of approximations, time efficiency and optimality of traffic signal settings, which is a new and important result. We also show that in terms of traffic optimization genetic algorithms give the best results comparing to other metaheuristics.
SSRN Electronic Journal, 2018
In this paper, we present how ideas from artificial intelligence field can be utilized in proxy m... more In this paper, we present how ideas from artificial intelligence field can be utilized in proxy modeling problem that is faced by actuarial departments of life insurance companies. The current approaches are reviewed, exposing their incapability to fully mimic the complexity and non-linearity of cash-flow projection models. In order to increase the quality of proxy models, we propose to apply selected machine learning algorithms as well as provide an overview of the theory behind them and present the numerical results with a comparison of model errors for different estimators. The study is performed on real data generated by a large reinsurance company. The text can serve as a guideline for companies willing to introduce machine learning algorithms in their proxy modeling processes.
arXiv: Quantum Physics, 2018
This text aims to present and explain quantum machine learning algorithms to a data scientist in ... more This text aims to present and explain quantum machine learning algorithms to a data scientist in an accessible and consistent way. The algorithms and equations presented are not written in rigorous mathematical fashion, instead, the pressure is put on examples and step by step explanation of difficult topics. This contribution gives an overview of selected quantum machine learning algorithms, however there is also a method of scores extraction for quantum PCA algorithm proposed as well as a new cost function in feed-forward quantum neural networks is introduced. The text is divided into four parts: the first part explains the basic quantum theory, then quantum computation and quantum computer architecture are explained in section two. The third part presents quantum algorithms which will be used as subroutines in quantum machine learning algorithms. Finally, the fourth section describes quantum machine learning algorithms with the use of knowledge accumulated in previous parts.
2019 6th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2019
We present a method for optimizing traffic signal settings which can be used for offline planning... more We present a method for optimizing traffic signal settings which can be used for offline planning and realtime adaptive traffic management. The method is based on metaheuristics efficiently exploring space of possible settings and evaluating candidate solutions using a microscopic traffic simulation or metamodels of simulations built using machine learning algorithms (e.g., neural networks, LightGBM). We present results of extensive experiments and compare different algorithms and their configurations in order to find the best approach in our use case. Experiments were carried out on a realistic road network of Warsaw (maps originated from the OpenStreetMap service) and showed that LightGBM may outperform neural networks in terms of accuracy of approximations, time efficiency and optimality of traffic signal settings, which is a new and important result. We also show that in terms of traffic optimization genetic algorithms give the best results comparing to other metaheuristics.
SSRN Electronic Journal, 2018
In this paper, we present how ideas from artificial intelligence field can be utilized in proxy m... more In this paper, we present how ideas from artificial intelligence field can be utilized in proxy modeling problem that is faced by actuarial departments of life insurance companies. The current approaches are reviewed, exposing their incapability to fully mimic the complexity and non-linearity of cash-flow projection models. In order to increase the quality of proxy models, we propose to apply selected machine learning algorithms as well as provide an overview of the theory behind them and present the numerical results with a comparison of model errors for different estimators. The study is performed on real data generated by a large reinsurance company. The text can serve as a guideline for companies willing to introduce machine learning algorithms in their proxy modeling processes.
arXiv: Quantum Physics, 2018
This text aims to present and explain quantum machine learning algorithms to a data scientist in ... more This text aims to present and explain quantum machine learning algorithms to a data scientist in an accessible and consistent way. The algorithms and equations presented are not written in rigorous mathematical fashion, instead, the pressure is put on examples and step by step explanation of difficult topics. This contribution gives an overview of selected quantum machine learning algorithms, however there is also a method of scores extraction for quantum PCA algorithm proposed as well as a new cost function in feed-forward quantum neural networks is introduced. The text is divided into four parts: the first part explains the basic quantum theory, then quantum computation and quantum computer architecture are explained in section two. The third part presents quantum algorithms which will be used as subroutines in quantum machine learning algorithms. Finally, the fourth section describes quantum machine learning algorithms with the use of knowledge accumulated in previous parts.