Not stated in source
2020 Needs review
Available
- Author
- B.E. Salami
- University
- University of Eastern Finland
- Country
- Finland
- Main specialisation
- AI in Healthcare › Convolutional Neural Networks
Nearly 17 million people die every year due to cardiovascular disease according to World Health Organization and one of the diseases associated with the human heart is arrhythmia.Arrhythmia is the irregularity and abnormality of heartbeat rhythm.To detect arrh…
Not stated in source
2020 Needs review
- Author
- J. Laakso
- University
- Tampere University
- Country
- Finland
- Main specialisation
- Deep Learning & Neural Networks › Predictive Analytics & Time Series
Not stated in source
2020 Needs review
- Author
- Nasrin Someeh
- University
- Not available
- Country
- Not available
- Main specialisation
- Deep Learning & Neural Networks
Not stated in source
2020 Needs review
- Author
- Norah M. Alnaim
- University
- Brunel University London
- Country
- United Kingdom
- Main specialisation
- Natural Language Processing › Speech Recognition
Human Computer Interaction (HCI) is a broad field involving different types of interactions including gestures.Gesture recognition concerns non-verbal motions used as a means of communication in HCI.A system may be utilised to identify human gestures to convey…
Not stated in source
2020 Needs review
- Author
- Basuki Winoto
- University
- Harvard University
- Country
- United States
- Main specialisation
- Natural Language Processing › Speech Recognition
Speech reading or lip reading is the understanding of spoken language while watching the speaker. It is a natural extension to increase comprehension when hearing becomes challenging. One attentively observes the speaker’s mouth movement as it forms the word.…
Not stated in source
2020 Needs review
- Author
- Xue-Qing Ma
- University
- Nanyang Technological University
- Country
- Singapore
- Main specialisation
- Natural Language Processing › Speech Recognition
Deep learning is a new research direction in the field of machine learning. It is a subclass of machine learning. Inspired by the way the human brain works, deep learning is a learning process that uses deep neural networks to address feature expression. In ma…
Master
2020 Verified
Available
- Author
- Zijing Zhang
- University
- University of Waikato
- Country
- New Zealand
- Main specialisation
- Deep Learning & Neural Networks › Transformers
This thesis aims to develop an efficient question generator for an automated tutoring system. Given a context passage with an answer, the question generator asks questions to help the reader learn new material. By utilizing the BERT model, this thesis experime…
Not stated in source
2020 Needs review
- Author
- David Morán Pomés
- University
- Not available
- Country
- Not available
- Main specialisation
- Deep Learning & Neural Networks › Transformers
Kernel methods (KM) and Artificial Neural Networks (ANN) are two of the main families of methods that are more widely spread nowadays in the world of Machine Learning, being the Support Vector Machine (SVM) and the Deep Learning Neural Network (DLNN) its most…
Master
2020 Verified
Available
- Author
- Анна Юрьевна Короткова
- University
- Ludwid Maxmilian's Universitat Munchen
- Country
- Germany
- Main specialisation
- Natural Language Processing › Large Language Models
In this master's thesis, we perform an analysis based on the language models BERT (Devlin et al., 2019), RoBERTa (Liu et al., 2019), DistilBERT (Sanh et al., 2020), ALBERT (Lan et al., 2019) and XLNET (Yang et al., 2019) whose architectures are based on the Tr…
Not stated in source
2020 Needs review
- Author
- Aniol Civit Bertran
- University
- Not available
- Country
- Spain
- Main specialisation
- AI in Healthcare
The increment of dependant people for the realization of Activities of Daily Living is a fact that comes implicit with the increase of population and their lifespan given by the modern technological progress. For this reason, Assistive Robotics is a field that…
Not stated in source
2020 Needs review
- Author
- Andreas Pentaliotis
- University
- Not available
- Country
- Not available
- Main specialisation
- Reinforcement Learning › Fairness, Privacy & Ethics
Overestimation bias is an inherent property of reinforcement learning algorithms that approximate maximum expected values by maximizing uncertain estimates. Since overestimation bias was identified in the literature, it has been generally considered to have a…
Not stated in source
2020 Needs review
- Author
- Katherine Wang
- University
- Massachusetts Institute of Technology
- Country
- United States
- Main specialisation
- Machine Learning › Predictive Analytics & Time Series
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020