Not stated in source
2023 Needs review
Available
- Author
- Daniil Kulik
- University
- Not available
- Country
- Canada
- Main specialisation
- AI in Healthcare › Medical Image Analysis
Ultrasound is a non-invasive, radiation-free portable imaging modality that offers real-time diagnostics in different clinical settings.Ultrasound video analysis can benefit from the rise of AI-powered applications in healthcare.However, access to ultrasound d…
Not stated in source
2023 Needs review
Available
- Author
- Li, Yupeng ; Linberg, Jonatan
- University
- Jönköping University
- Country
- Sweden
- Main specialisation
- Generative AI › GANs
At present, state-of-the-art deep learning music generation systems require a lot time and hardware resources to develop. This means that they are almost exclusively available to large companies. In order to reduce these requirements, more efficient techniques…
Not stated in source
2023 Needs review
- Author
- Xiang Lin
- University
- Nanyang Technological University
- Country
- Singapore
- Main specialisation
- Natural Language Processing › Large Language Models
The advances in deep learning have led to great achievements in many Natural Language Processing (NLP) tasks. With the nature of language, i.e., sequential data, most NLP tasks can be framed into the sequence learning framework, such as text generation. As one…
Not stated in source
2023 Needs review
- Author
- Marek Behún
- University
- Not available
- Country
- Czech Republic
- Main specialisation
- Computer Vision › Graph Neural Networks
Recently, the research on Graph Neural Networks (GNNs) made it possi- ble to apply deep learning techniques to graph-structured data. In this thesis, we explore the application of GNNs to Social Network Analysis (SNA). We build and compare deep learning models…
Not stated in source
2023 Needs review
- Author
- Kunze Wang
- University
- The University of Sydney
- Country
- Australia
- Main specialisation
- Natural Language Processing › Graph Neural Networks
By constructing graph-structured data from the input data, Graph Neural Network (GNN) enhances the performance of numerous Natural Language Processing (NLP) tasks. In this thesis, we mainly focus on two aspects of NLP: text classification and knowledge graph c…
Not stated in source
2023 Needs review
- Author
- Bishal Lakha
- University
- Boise State University
- Country
- United States
- Main specialisation
- Deep Learning & Neural Networks › Transformers
Detecting malicious behavior is becoming increasingly crucial as the internet becomes more prevalent. This problem can be formulated as an anomaly detection task on provenance data, where attacks are detectable as anomalies in the behavior of the system. The a…
Not stated in source
2023 Needs review
- Author
- Fateme Fotouhi
- University
- Not available
- Country
- Not available
- Main specialisation
- AI in Healthcare › Federated Learning
Autonomous intelligent agents possess the capability to autonomously perceive their environment and make decisions based on their prior knowledge or learning experiences. The field of Deep Learning (DL) has witnessed significant advancements in recent years, l…
Not stated in source
2023 Needs review
Available
- Author
- Keli Rodrigues do Amaral Benin
- University
- Not available
- Country
- Not available
- Main specialisation
- Natural Language Processing › Data Mining
Introduction: In recent decades, there has been an increase in the amount of information processed, stored and made available in documents, mainly made available in the digital environment. Due to the exponential increase in the amount of information, manual m…
Not stated in source
2023 Needs review
- Author
- MORMILLE LUIZ HENRIQUE BARBOSA
- University
- Not available
- Country
- Japan
- Main specialisation
- Deep Learning & Neural Networks › Transformers
In recent years, the Transformer achieved remarkable results in computer vision related tasks, matching, or even surpassing those of convolutional neural networks (CNN). However, unlike CNNs, those vision transformers lack strong inductive biases and, to achie…
Not stated in source
2023 Needs review
Available
- Author
- Yingzhu Zhao
- University
- Nanyang Technological University
- Country
- Singapore
- Main specialisation
- Deep Learning & Neural Networks › Transformers
As a result of advancement in deep learning and neural network technology, end-to-end models have been introduced into automatic speech recognition (ASR) successfully and achieved superior performance compared to conventional hybrid systems. End-to-end models…
Not stated in source
2023 Needs review
Available
- Author
- Maxwell Clarke
- University
- Not available
- Country
- New Zealand
- Main specialisation
- Deep Learning & Neural Networks › Transformers
Transformer models have been quickly taking over many tasks in the field of deep learning, due to their versatility while maintaining high performance. This thesis provides an introduction to transformer models, presents experiments with new ways of sampling d…
Not stated in source
2023 Needs review
- Author
- Brendan William Duke
- University
- University of Toronto
- Country
- Canada
- Main specialisation
- Deep Learning & Neural Networks › Transformers
Deep learning (DL) algorithms have produced superior results for a variety of vision, language, and speech processing tasks, but have proven to be power and compute-hungry. In the past, hardware advancements have met the growing need for compute. Yet in recent…