Implementation of recurrent neural network and application for next word prediction

Autor: Martinović, Ivan
Přispěvatelé: Šnajder, Jan
Jazyk: chorvatština
Rok vydání: 2021
Předmět:
Popis: Duboko učenje danas se intenzivno primjenjuje na različitim zadacima unutar područja umjetne inteligencije. Unutar obrade prirodnog jezika povratne neuronske mreže već duže vrijeme imaju važnu ulogu, stoga je razumijevanje teorije koja stoji iza takvih struktura doista važno. Cilj ovoga rada bilo je upravo dubinsko razumijevanje teorije koja stoji iza povratnih neuronskih mreža te umjetnih neuronskih mreža općenito, a to razumijevanje dobiveno je programskom implementacijom tih modela. Ovaj završni rad podijeljen je u dva dijela. U prvom dijelu predstavljene su slojevita i povratna neuronska mreže te je prikazana njihova implementacija. Drugi dio prikazuje primjenu povratnih neuronskih mreža na zadatku predviđanja sljedeće riječi. Today, deep learning is intensively used for solving different tasks regarding artificial intelligence. Recurrent neural networks have had a significant role in natural language processing for a long time now and that is why understanding the theory behind such structures is of great importance. That is why the main objective of this thesis was to understand the theory behind recurrent neural networks and artificial neural networks in general, which was achieved through the implementation of those models. The thesis is divided into two major parts. The first part introduces fully connected neural networks and recurrent neural networks, as well as their implementations. The second part focuses on the use of recurrent neural networks in a next word prediction task.
Databáze: OpenAIRE