Performance Interfaces for Network Functions

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

During the Artificial Intelligence (AI) revolution of the past decades, deep neural networks have been widely used and have achieved tremendous success in visual recognition. Unfortunately, deploying deep models is challenging because of their huge model s ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

Reading out neuronal activity from three-dimensional (3D) functional imaging requires segmenting and tracking individual neurons. This is challenging in behaving animals if the brain moves and deforms. The traditional approach is to train a convolutional n ...

In the recent years, Deep Neural Networks (DNNs) have managed to succeed at tasks that previously appeared impossible, such as human-level object recognition, text synthesis, translation, playing games and many more. In spite of these major achievements, o ...

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

In this thesis, we advocate that Computer-Aided Engineering could benefit from a Geometric Deep Learning revolution, similarly to the way that Deep Learning revolutionized Computer Vision. To do so, we consider a variety of Computer-Aided Engineering pr ...

We develop a novel 2D functional learning framework that employs a sparsity-promoting regularization based on second-order derivatives. Motivated by the nature of the regularizer, we restrict the search space to the span of piecewise-linear box splines shi ...

Security system designers favor worst-case security metrics, such as those derived from differential privacy (DP), due to the strong guarantees they provide. On the downside, these guarantees result in a high penalty on the system's performance. In this pa ...

The application of machine learning to theoretical chemistry has made it possible to combine the accuracy of quantum chemical energetics with the thorough sampling of finite-temperature fluctuations. To reach this goal, a diverse set of methods has been pr ...

Failures far away from a user should intuitively be less likely to affect that user. Today's ecosystem miserably fails this test, however, despite high-availability best practices. Correlated and cascading failures – triggered by misconfigurations, bugs, a ...

A recent series of theoretical works showed that the dynamics of neural networks with a certain initialisation are well-captured by kernel methods. Concurrent empirical work demonstrated that kernel methods can come close to the performance of neural netwo ...

The hydropower sector has recently raised the interest in pump as turbine (PaT) that can be a valid trade-off between capital cost and performance in micro-scale installations. Nevertheless, the modest efficiency of PaTs often restricts their exploitation. ...

Optical imaging through complex media, such as biological tissues or fog, is challenging due to light scattering. In the multiple scattering regime, wavefront shaping provides an effective method to retrieve information; it relies on measuring how the prop ...

The advent of software network functions calls for stronger correctness guarantees and higher performance at every level of the stack. Current network stacks trade simplicity for performance and flexibility, especially in their driver model. We show that p ...

Performance Interfaces for Network Functions

Chat with Graph Search

Improving the Training of Compact Neural Networks for Visual Recognition

Deep Learning Generalization with Limited and Noisy Labels

Automated neuron tracking inside moving and deforming C. elegans using deep learning and targeted augmentation

Theory of Deep Learning: Neural Tangent Kernel and Beyond

Robust Training and Verification of Deep Neural Networks

Synthesis and Analysis of 3D shapes with Geometric Deep Learning in Computer-Aided Engineering

Learning of Continuous and Piecewise-Linear Functions With Hessian Total-Variation Regularization

Bayes Security: A Not So Average Metric

Local Kernel Regression and Neural Network Approaches to the Conformational Landscapes of Oligopeptides

Immunizing Systems from Distant Failures by Limiting Lamport Exposure

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

Numerical investigation on the volute cutwater for pumps running in turbine mode

Physics-based neural network for non-invasive control of coherent light in scattering media

A Simpler and Faster NIC Driver Model for Network Functions