diplomsko delo
Tomaž Piko (Author), Aleš Holobar (Mentor), Mladen Borovič (Co-mentor), Milan Ojsteršek (Co-mentor)

Abstract

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.

Keywords

pogovorni roboti;rekurentne nevronske mreže;celica LSTM;obdelava naravnih jezikov;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [T. Piko]
UDC: 004.934(043.2)
COBISS: 38731523 Link will open in a new window
Views: 413
Downloads: 35
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Chatbot implementation using a LSTM recurrent neural network
Secondary abstract: 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.
Secondary keywords: chatbots;recurrent neural networks;LSTM cell;natural language processing;
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: IX, 52 f.
ID: 12004561