Publication
Nine recommendations for the governance of AI systems
Related publications (40)
Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation
Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence.Althou ...
EPFL2024Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection
Supervised machine learning models are receiving increasing attention in electricity theft detection due to their high detection accuracy. However, their performance depends on a massive amount of labeled training data, which comes from time-consuming and ...
Piscataway2024Aiming beyond slight increases in accuracy
Owing to the diminishing returns of deep learning and the focus on model accuracy, machine learning for chemistry might become an endeavour exclusive to well-funded institutions and industry. Extending the focus to model efficiency and interpretability wil ...
NATURE PORTFOLIO2023Optimizing in-situ monitoring for laser powder bed fusion process: Deciphering acoustic emission and sensor sensitivity with explainable machine learning
Christian Leinenbach, Sergey Shevchik, Rafal Wróbel
Metal-based Laser Powder Bed Fusion (LPBF) has made fabricating intricate components easier. Yet, assessing part quality is inefficient, relying on costly Computed Tomography (CT) scans or time-consuming destructive tests. Also, intermittent inspection of ...
Lausanne2023The Virtue of Complexity in Return Prediction
Much of the extant literature predicts market returns with "simple" models that use only a few parameters. Contrary to conventional wisdom, we theoretically prove that simple models severely understate return predictability compared to "complex" models in ...
Hoboken2023Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU
Nahal Mansouri, Sahand Jamal Rahi
Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.Objecti ...
FRONTIERS MEDIA SA2022Practical Byzantine-resilient Stochastic Gradient Descent
Sébastien Louis Alexandre Rouault
Algorithms are everywhere.The recipe for the frangipane cake is an algorithm.If all the listed ingredients are available and the cook is sufficiently deft, after a finite number of small, well-defined steps a delicious dessert will exit the oven.Now, what ...
EPFL2022HDTorch: Accelerating Hyperdimensional Computing with GP-GPUs for Design Space Exploration
David Atienza Alonso, Tomas Teijeiro Campo, William Andrew Simon, Una Pale
The HyperDimensional Computing (HDC) Machine Learning (ML) paradigm is highly interesting for applications involving continuous, semi-supervised learning for long-term monitoring. However, its accuracy is not yet on par with other ML approaches, necessitat ...
Association for Computing MachineryNew YorkNYUnited States2022Lifelong Machine Learning with Data Efficiency and Knowledge Retention
Artificial intelligence (AI) and machine learning (ML) have become de facto tools in many real-life applications to offer a wide range of benefits for individuals and our society. A classic ML model is typically trained with a large-scale static dataset in ...
EPFL2021Demonstrator Surface For Machine Learning Algorithm
In the field of haptic feedback, LAI is working on a way of localizing impact vibrations through machine learning algorithms. In this semester project, the goal is to extend a one-dimensional system into a two-dimensional system with a demonstrator surface ...
2021