Combining Structural and Timing Errors in Overclocked Inexact Speculative Adders

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.

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for futur ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Examining the performance of an existing bridge requires information on several aspects, such as design choices, material properties, and ongoing degradation processes. It often happens that some critical information is not available. The traditional appro ...

Most codes of practice adopt a semi probabilistic design approach for the dimensioning and assessment of structures. Accordingly, structural safety is ensured by performing limit state verifications using design values determined with adequately calibrated ...

Bending-active elastica beam is a structural configuration that is based on the elastic deformation of an initially straight beam. This deformation occurs when horizontal displacements are applied to a sliding support, causing the beam to bend into an arch ...

Carefully extracting reinforced concrete (RC) elements from soon-to-be demolished structures and reusing them as load-bearing components is an emerging circular low-carbon alternative to building new structures. As floor construction typically accounts for ...

The development of Ultra-High Performance Fibre-Reinforced Cementitious Composite (UHPFRC) has enabled the design of lightweight constructions. Although the greenhouse gas emissions of UHPFRC per volume are higher than that of conventional concr ...

Ultra-high performance fiber reinforced cementitious composite (UHPFRC) is a modern class of cementitious building materials. Because of its superior mechanical properties and durability, it is increasingly used globally to rehabilitate, strengthen and mod ...

In this thesis, we conduct a comprehensive investigation into structural instabilities of both elastic and magneto-elastic beams and shells, resulting in a creative proposal to design a programmable braille reader. Methodologically, we combine numerical si ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

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. Altho ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

The EU DEMO Tokamak is foreseen to be equipped with an electron cyclotron (EC) system for plasma heating, magnetohydrodynamic (MHD) control, and thermal instability suppression. Up to six launchers will be installed into equatorial ports with the aim to in ...

Hybrid methylammonium (MA) lead halide perovskites have emerged as materials exhibiting excellent photovoltaic performance related to their rich structural and dynamic properties. Here, we use multifrequency (X-, Q-, and W-band) electron paramagnetic reson ...

Monitoring the health of complex industrial assets is crucial for safe and efficient operations. Health indicators that provide quantitative real-time insights into the health status of industrial assets over time serve as valuable tools for, e.g., fault d ...

Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limi ...

Combining Structural and Timing Errors in Overclocked Inexact Speculative Adders

Chat with Graph Search

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Plasma state monitoring and disruption characterization using multimodal VAEs

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

A global framework for data-informed bridge examination

Influence of model uncertainty and long term deformations in action effects calculation in reinforced concrete structures

Short-term behavior of glass fiber-polymer composite bending-active elastica beam under service load application

FLO:RE – A new floor system made of reused reinforced concrete and steel elements

Methods to assess the carbon footprint of structures involving UHPFRC elements

Influence of fiber orientation on the tensile behavior of UHPFRC and reinforced UHPFRC under static and fatigue loadings

Instabilities in Elastic and Magneto-Elastic Beams and Shells: from Shell Buckling to the Design of a Programmable Braille Reader

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Topics in statistical physics of high-dimensional machine learning

Robust machine learning for neuroscientific inference

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Design Progress of Structural Components of the EU DEMO EC Equatorial Launcher

Probing structural and dynamic properties of MAPbCl3 hybrid perovskite using Mn2+ EPR

Learning Informative Health Indicators Through Unsupervised Contrastive Learning

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds