Machine Learning aims to enable computers to learn from the world around them the same way as humans do, and it has revolutionized the world in the last few years. Deep learning, a particular method of machine learning, has played a crucial role in enabling several applications such as self-driving cars, speech-enabled user interfaces, medical image analysis, web search engines, recommendation systems, security & surveillance, object detection and recognition, and object tracking, etc. Though substantial progress has already been made in the development of machine learning algorithms and their underlying theory, several challenges remain.
For example, how to train deep models in the absence of large amounts of training data? How to build deep models for resource-constrained mobile devices? How to improve the generalization performance of deep neural networks? How to enable deep models to adapt and generalize to unknown target domains? How to protect deep models from adversarial attacks?
Our research focuses on finding answers to these problems.
of the laboratory
The Machine Learning & Knowledge Representation (MlKr) lab focuses on theoretical and applied aspects of Machine Learning and Knowledge Representation in various domains. Machine learning deals with the study of computational methods that enable machines to learn from data.
— Data Augmentation
— Domain Adaptation
— Domain Generalization
— Hierarchical Learning
— Variational Inference
— Resource-efficient Neural Computing
— Adversarial Learning
Adil Mehmood Khan
Head of the laboratory
Louise Jonatha Pires De Araujo
Aorta segmentation on CT scan images
Aortic shunting operations need to be planned accurately. To do this, surgeons need to know exact sizes of aorta. This project creates a tool for medical imaging software, which will automate measuring aorta using computer vision and machine learning methods. Results of this project will be later used for other applications in medical image analysis
Semantic indexing for edge devices
Building a small, accurate index for large scale text and images datasets to be used on edge devices. Direct document recommendation, distributed indexing strategy, duplicate detection, content-based image retrieval
Event graph analysis can bring significant benefit in community mining, recommendations and predictions. Event recommendations for people$ event and expert analysis, ranking and recommendation
A project is a set of Deep Learning models, Information Retrieval tools and Backend code that are altogether form a web-service that can recommend a single dress/clothing or potentially a set/a look, given a photo of a person dressed/a piece of clothing/a screenshot from a movie (the input is yet to be decided)
Investigation the effect of domain gaps on the performance of machine learning models performances for different applications. Our first step was to measure the change in datasets and propose a Domain Adaptation technique for fixing this problem in images, which we extended to work on video datasets and text. We also proposed a new method for domain généralisation based on adversarial reconstruction loss. We are currently investigating the effect of deploying the same model for medical imaging on different MRI scans (MRI-Sequences).
Neural Machine Translation
Our goal is to find new effective ways to leverage such additional sources as monolingual data or parallel corpora for related languages. Together with our students, we made the review of the current approaches to utilize monolingual data in low-resource machine translation.
Neural networks for mobile devices
The main research objectives of the work are: understand the capabilities of mobile devices presented on the market for deep learning solutions; identify common obstacles for deploying modern neural network architectures; explore the efficiency of Neural Architecture Search approaches for compact networks; and suggest a framework for generation efficient architectures.
Deep Learning in Industry
Two sub-projects are being implemented. The goal of the first sub-project is to develop and test algorithms for detecting activities consruction and railway workers, and the estimated time of work operations using video footage of performed works. The second sub-project is about implementing a deep learning approach to perform tree canopy area segmentation for a digital forest mapping system