20.500.12556/DKUM-77606 Izdelava pogovornega robota z rekurentno nevronsko mrežo LSTM diplomsko delo Chatbot implementation using a LSTM recurrent neural network V diplomskem delu so v prvem delu najprej predstavljeni pogovorni roboti in njihovi tipi, nato rekurentne nevronske mreže ter delovanje različnih celic, ki jih pri njih najpogosteje srečujemo. V drugem delu pa je prikazan primer implementacije in učenja rekurentne nevronske mreže LSTM (Long Short-Term Memory) ter izdelava mobilne aplikacije, v kateri lahko pisno komuniciramo z izdelano mrežo oziroma našim pogovornim robotom v slovenskem ali angleškem jeziku. The first part of this diploma thesis describes chatbots and their types. We then describe recurrent neural networks and how their most frequently used types of cells work. The second part shows an example of implementing and training a recurrent neural network LSTM (Long Short-Term Memory) and developing a mobile application in which we can communicate with the created neural network and our own chatbot via text in the Slovenian or English language. pogovorni roboti rekurentne nevronske mreže celica LSTM obdelava naravnih jezikov chatbots recurrent neural networks LSTM cell natural language processing true true false [T. Piko] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2020-09-07 10:18:26 2020-11-03 09:57:25 2022-08-09 15:47:43 2020-11-25 03:20:08 2020 0 Maribor 0 Maribor IX, 52 f. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.934(043.2) 38731523 URN:SI:UM:DK:VVTDQHUC UN_Piko_Tomaz_2020.pdf UN_Piko_Tomaz_2020.pdf 1 D6AB9D8928D9C18BE691FE242222D270 5207d0cc5a28d3136eb4a5cabf476ef3abb76ba8b1527bcee3c9efdc955fa55e cd01037b-7c11-11eb-bb7a-00155d0001ca 20.500.12556/dkum/70fcbf82-06d6-4da5-99c4-baf7ba31810d https://dk.um.si/Dokument.php?lang=slv&id=145499 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0