Blar i NTNU Open på forfatter "Ruocco, Massimiliano"
-
A Continuous Approach to Controllable Text Generation using Generative Adversarial Networks
Helgøy, Dag Inge; Lund, Markus (Master thesis, 2017)The challenges of training generative adversarial network (GAN) to produce discrete tokens, have seen a considerable amount of work in the past year. However, the amount of successful work on applying deep generative models ... -
A Deep Learning-Based Method for Regional Wind Power Production Volume Prediction
Liodden, Erik (Master thesis, 2020)Målet med denne studien var å estimere produksjonsvolumet av vindkraft i en stor geografisk region gitt de numeriske vær-datane (NWP) over regionen og metoder basert på dyp læring. Et presist estimat for fremtidig ... -
A deep network model for paraphrase detection in short text messages
Agarwal, Basant; Ramampiaro, Heri; Langseth, Helge; Ruocco, Massimiliano (Journal article; Peer reviewed, 2018)This paper is concerned with paraphrase detection, i.e., identifying sentences that are semantically identical. The ability to detect similar sentences written in natural language is crucial for several applications, such ... -
Active One-shot Learning with Memory-Augmented Neural Networks
Kvistad, Andreas Henriksen (Master thesis, 2018)This thesis aims at learning an Active Learning agent for one-shot predictions of texts and images via Reinforcement Learning. There are three different models being implemented, where the baseline is a LSTM network, and ... -
Attention Mechanisms in Hierarchical Session-Based Recommendation
Lervik, Kristoffer (Master thesis, 2018)The use of attention mechanisms in different applications of recurrent neural networks has yielded significantly higher accuracies, but their use in session-based recommender systems is largely unexplored. In addition to ... -
Conversational Language Models for Low-Resource Speech Recognition
Burud, Simen (Master thesis, 2021)Automatiske talegjenkjenningsystemer transkiberer tale til tekst. Slike systemer har et bredt spekter av praktiske bruksområder, fra dikteringsverktøy som forenkler kommunikasjon for personer med hørsels - eller motoriske ... -
Curriculum Learning for agents in pixel based 3D Environments
Thorbjørnsen, Per Torgrim Frøstrup (Master thesis, 2017)This thesis explores Curriculum Learning in Deep-RL. The focus is on VizDoom, an 3D environment with pixels as state representation. Two new curriculum methods are proposed. One simplifies the frames by using image processing ... -
Data Efficient Deep Reinforcement Learning through Model-Based Intrinsic Motivation
Nylend, Mikkel Sannes (Master thesis, 2017)In the last few years we have experienced great advances in the field of reinforcement learning (RL), much thanks to deep learning. By introducing deep neural networks in RL it is possible to have agents learn complex ... -
Deep Contextual Grid Triplet Network for Context-Aware Recommendation
Aftab, Sofia; Ramampiaro, Heri; Langseth, Helge; Ruocco, Massimiliano (Peer reviewed; Journal article, 2023)Modeling contextual information is a vital part of developing effective recommender systems. Still, existing work on recommendation algorithms has generally put limited focus on the effective treatment of contextual ... -
Deep Reinforcement Learning and Generative Adversarial Networks for Abstractive Text Summarization
Lie, Borgar Rannem; Kalmar, Alf Niklas Håkonsen (Master thesis, 2018)News articles, papers and encyclopedias, among other texts can be time-consuming to digest. Often, you are not interested in reading all the material, but only some of it. Summaries can be useful to get a grasp of what ... -
Deep Representation Learning for Personalised High Granularity Cycling Performance Prediction
Fauskanger, Henrik; Martinsen, Claus (Master thesis, 2021)Abstract will be available on 2024-07-12 -
Deep Representation Learning for Personalised High Granularity Cycling Performance Prediction
Fauskanger, Henrik; Martinsen, Claus (Master thesis, 2021)Abstract will be available on 2024-07-12 -
Defining Roles in Transaction Networks Using Deep Learning
Vikanes, Eirik (Master thesis, 2018)Recent years have seen an immense increase in the amount of data our generated by humans. This data takes many different shapes and forms, and one of the types we find most often is in the form of network data. In order ... -
Domain general Active Learning strategies using inter-sample similarity and Reinforcement Learning
Hoxmark, Bjørn; Wilhelmsen, Jørgen (Master thesis, 2018)One of the major drawbacks of deep learning is the amount of labeled training data required in order to reach acceptable performance. This labeled data may be difficult and expensive to obtain. The goal of active learning ... -
Dual Active Sampling: A batch-mode active learning method
Phan, Johan (Master thesis, 2019)Nylig har CNN vist enestående suksess innen datasyn, spesielt for utfordrende bildeklassifiseringsoppgaver ved å basere seg på en universal tilnærming, mao. trene en dyp model på et massivt datasett med veiledende eksempler. ... -
Evolving Knowledge And Structure Through Evolution-based Neural Architecture Search
Wang, Magnus Poppe (Master thesis, 2019)Meta learning is a step towards an artificial general intelligence, where neural architecture search is at the forefront. The methods dominating the field of neural architecture search are recurrent neural networks and ... -
Exploring Cells and Context Approaches for RNN Based Conversational Agents
Johnsrud, Simen; Christensen, Silje (Master thesis, 2017)Natural Language Processing is a challenging field within Artificial Intelligence, and building bots and conversational agents have been pursued by many researchers over the last decades. These agents should output reasonable ... -
Generative Adversarial Networks for Unsupervised Anomaly Detection in Multivariate Time-Series Telecommunications Data
Vang, Sigurd Nybakk (Master thesis, 2021)Etter hvert som nettverksinfrastrukturen i telekommunikasjonsdomenet blir mer kompleks, blir det stadig viktigere å utvikle systemer som er i stand til ̊a automa-tisere effektiv og nøyaktig deteksjon av avvik. Slike ... -
Geo-Temporal Mining and Searching of Events from Web-based Image Collections
Ruocco, Massimiliano (Doktoravhandlinger ved NTNU, 1503-8181; 2014:159, Doctoral thesis, 2014)The proliferation of Web- and social media-based photo-sharing applications have not only opened many possibilities but also resulted in new needs and challenges. They have resulted in a large amount of personal photos ... -
Global Transformer Architecture for Indoor Room Temperature Forecasting
Clemente, Alfredo; Nocente, Alessandro; Ruocco, Massimiliano (Peer reviewed; Journal article, 2023)A thorough regulation of building energy systems translates in relevant energy savings and in a better comfort for the occupants. Algorithms to predict the thermal state of a building on a certain time horizon with a good ...