Sökning: "seq2seq"

Visar resultat 6 - 10 av 11 uppsatser innehållade ordet seq2seq.

1. 6. Using Attention-based Sequence-to-Sequence Neural Networks for Transcription of Historical Cipher Documents

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Han Renfei; [2020]
   Nyckelord :;

   Sammanfattning : Encrypted historical manuscripts (also called ciphers), containing encoded information, provides a useful resource for giving new insight into our history. Transcribing these manuscripts from image format to computer readable format is a necessary step for decrypting them. LÄS MER

3. 7. Encoder-Decoder Networks for Cloud Resource Consumption Forecasting

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Sami Mejdi; [2020]
   Nyckelord :Telecommunications; Cloud; Time Series; Forecasting; Encoder-Decoder; Deep Learning; Machine Learning; Telekommunikation; Moln; Tidsserie; Prognoser; Encoder-Decoder; Djupinlärning; Maskininlärning;

   Sammanfattning : Excessive resource allocation in telecommunications networks can be prevented by forecasting the resource demand when dimensioning the networks and then allocating the necessary resources accordingly, which is an ongoing effort to achieve a more sustainable development. In this work, traffic data from cloud environments that host deployed virtualized network functions (VNFs) of an IP Multimedia Subsystem (IMS) has been collected along with the computational resource consumption of the VNFs. LÄS MER

4. 8. Molecular Optimization Using Graph-to-Graph Translation

   Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för matematik och matematisk statistik

   Författare :Emil Sandström; [2020]
   Nyckelord :Machine learning; Deep learning; Molecular Optimization; Transformer; Seq2seq; Graph-to-Graph Translation Ac;

   Sammanfattning : Drug development is a protracted and expensive process. One of the main challenges indrug discovery is to find molecules with desirable properties. Molecular optimization is thetask of optimizing precursor molecules by affording them with desirable properties. LÄS MER

5. 9. Creating Dynamic Robot Utterances in Human-Robot Social Interaction : Comparison of a Selection-Based Approach and a Neural Network Approach on Giving Robot Responses in Conversations

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Philip Andersson; E Soon Ko; [2019]
   Nyckelord :;

   Sammanfattning : This study examines two different approaches to dialogue management system in order to achieve dynamic utterances in human-robot social interactions. This was done in order to determine whether Robot Assisted Language Learning is viable as a solution to the current teacher shortage situation in Sweden. LÄS MER

7. 10. Study of Semi-supervised Deep Learning Methods on Human Activity Recognition Tasks

   Master-uppsats, KTH/Robotik, perception och lärande, RPL

   Författare :Shiping Song; [2019]
   Nyckelord :Semi-supervised learning; Sequence learning; Human activity recognization; DeepConvLSTM; Seq2seq model;

   Sammanfattning : This project focuses on semi-supervised human activity recognition (HAR) tasks, in which the inputs are partly labeled time series data acquired from sensors such as accelerometer data, and the outputs are predefined human activities. Most state-of-the-art existing work in HAR area is supervised now, which relies on fully labeled datasets. LÄS MER