Inhalt

[ 993MLPELRNV19 ] VL (*)LSTM and Recurrent Neural Nets

Versionsauswahl
(*) Leider ist diese Information in Deutsch nicht verfügbar.
Workload Ausbildungslevel Studienfachbereich VerantwortlicheR Semesterstunden Anbietende Uni
3 ECTS M1 - Master 1. Jahr Artificial Intelligence Sepp Hochreiter 2 SSt Johannes Kepler Universität Linz
Detailinformationen
Quellcurriculum Masterstudium Artificial Intelligence 2021W
Ziele (*)In this class, students will learn about Recurrent neural networks (RNNs) and Long Short Term Memory (LSTM), types of neural networks that are very commonly used for predicting sequential data, such as time-series, text or DNA. We will cover both theoretical fundamentals and advanced applications. It is expected that students visiting this class already have a solid understanding of deep learning.
Lehrinhalte (*)
  • Basics of sequence prediction
  • Recurrent neural networks
  • Vanishing Gradients and LSTMs
  • Attention Models
  • Memory Models (e.g. Neural Turing Machine)
  • Autoregressive Sequence Models and Transformers (PixelRNN, ByteNet, Transformers)
  • Applications in NLP (e.g. next character prediction, language modelling, sentiment analysis)
Beurteilungskriterien (*)Exam
Abhaltungssprache Englisch
Literatur (*)Lecture notes and slides
Lehrinhalte wechselnd? Nein
Präsenzlehrveranstaltung
Teilungsziffer -
Zuteilungsverfahren Direktzuteilung