The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...
Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...
As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...
The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...
While largely neglected over decades during which adaptive immunity captured most of the attention, innate immune mechanisms have now become central to our understanding of immunology. Innate immunity provides the first barrier to infection in vertebrates, ...
In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...
Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...
Surrogate-based optimization is widely used for aerodynamic shape optimization, and its effectiveness depends on representative sampling of the design space. However, traditional sampling methods are hard-pressed to effectively sample high-dimensional desi ...
The COVID-19 pandemic has led to a significant increase in working from home worldwide, making the workfrom-home (WFH) setting a crucial context for studying the influence of indoor environmental quality (IEQ) on workers' well-being and productivity. A nar ...
Statistical (machine-learning, ML) models are more and more often used in computational chemistry as a substitute to more expensive ab initio and parametrizable methods. While the ML algorithms are capable of learning physical laws implicitly from data, ad ...
Modern machine learning (ML) models are capable of impressive performances. However, their prowess is not due only to the improvements in their architecture and training algorithms but also to a drastic increase in computational power used to train them.|S ...
Drosophila melanogaster, commonly known as the "fruit fly", is a genetically tractable model organism widely used to study biological processes, notably the innate immune system. The advent of novel genome editing technologies, such as the CRISPR-Cas9 syst ...
As modern machine learning continues to achieve unprecedented benchmarks, the resource demands to train these advanced models grow drastically. This has led to a paradigm shift towards distributed training. However, the presence of adversariesâ whether ma ...
In-network devices around the world monitor and tamper with connections for many reasons, including intrusion prevention, combating spam or phishing, and country-level censorship. Connection tampering seeks to block access to specific domain names or keywo ...
The present invention generally relates to the field of intestinal health, disorders associated with aberrant microbiota and/or archaea-deficiency, and early-life immune system development. The present invention more specifically relates to M. smithii and ...
Hepatitis B virus remains a major medical burden with more than 250 million chronically infected patients worldwide and 900,000 deaths each year, due to the disease progression towards severe complications (cirrhosis, hepatocellular carcinoma). Despite the ...
The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...
Investigating the dynamic activities of protein expression and signaling in living organisms is a crucial focus of intense research aimed at elucidating the processes that underlie disease progression and improving treatments and drug development. Resolvin ...
The use of CAR technologies has revolutionized cancer treatment. Their unprecedented efficacy against B cell malignancies has opened the doors for a lot of excitement and research in the field. These synthetic receptors are composed of an antigen recogniti ...
We present Epidemic Learning ( EL ), a simple yet powerful decentralized learning (DL) algorithm that leverages changing communication topologies to achieve faster model convergence compared to conventional DL approaches. At each round of EL, each node sen ...
