| Seznam |
| Téma: | Deep Learning Based Approach for Solving Production Scheduling Problems |
|---|---|
| Vedoucí: | Přemysl Šůcha |
| Vypsáno jako: | Práce v týmu a její organizace |
| Popis: | Algorithms for combinatorial problems, e.g. production scheduling, often requires significant specialized knowledge. Therefore, it is usually not possible to take an algorithm that works well on a certain type of instances and use it on instances having a different character. In this case, it would be advantageous to have a mechanism able to analyze the new instances and adopt the behavior of the combinatorial algorithm, i.e. a method that is known as the data-driven approach. The aim of this project is to take a simple combinatorial problem, e.g. a simple production scheduling problem, and design a machine learning based algorithm able to solve it. 
|
| Pokyny: | 1. On a provided software project, study a way to design, train and use deep neural networks.
2. Analyze a selected production scheduling problem. 3. Design an algorithm for the selected problem including the deep neural network that will be used in the algorithm and implement them. 4. Propose a way to generate training data sets. 5. Evaluate performance of the algorithm |
| Literatura: | [1] Oriol Vinyals, Meire Fortunato, Navdeep Jaitly, Pointer Networks, https://arxiv.org/abs/1506.03134v2, 2015. [2] Anton Milan, S. Hamid Rezatofighi, Ravi Garg, Anthony Dick, Ian Reid, Data-Driven Approximations to NP-Hard Problems, AAAI Conference on Artificial Intelligence, 2017. |
| Vypsáno dne: | 13.02.2018 |
| Max. počet studentů: | 5 |
| Přihlášení studenti: | |