Impact of Memory Voltage Scaling on Accuracy and Resilience of Deep Learning Based Edge Devices

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.

This paper focuses on the operational characteristics of a medium voltage resonant DC transformer based on a split capacitor IGCT 3L-NPC leg. The study delves into both the dynamic and static balancing aspects of the 3L-NPC when operating in a two-level, 5 ...

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 ...

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that theoretical resul ...

The medium-voltage (MV) dual active bridge (DAB) converter with series-connected SiC (S-SiC) MOSFETs is a promising solution for high-power-density isolated dc/dc converter. To improve the voltage sharing and reliability of S-SiC, relatively large snubber ...

The Dynamic Aperture is an important concept for the study of non-linear beam dynamics in a circular accelerator. The DA is defined as the extent of the phase-space region in which the particle's motion remains bounded over a finite number of turns. Such a ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

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 ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

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 ...

Ultrafast ultrasound imaging achieves high frame rates but results in lower image quality compared to focused acquisitions. Convolutional neural networks (CNNs) have emerged as effective tools for reducing diffraction artifacts and enhancing the quality of ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Object detection is crucial in video analytics pipelines, but there is a need to optimize deep neural networks (DNNs)-based object detection for resource-constrained Internet of Things (IoT) devices. The computational constraints inherent to the IoT device ...

We perform an error analysis of a fully discretised Streamline Upwind Petrov Galerkin Dynamical Low Rank (SUPG-DLR) method for random time-dependent advection-dominated problems. The time integration scheme has a splitting-like nature, allowing for potenti ...

Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemic ...

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 ...

Impact of Memory Voltage Scaling on Accuracy and Resilience of Deep Learning Based Edge Devices

Chat with Graph Search

Static and Dynamic Voltage Balancing for an IGCT-Based Resonant DC Transformer

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

EdgeAI-Aware Design of In-Memory Computing Architectures

High-performance deep spiking neural networks with 0.3 spikes per neuron

Phase Shift Angle Segmentation Modulation for Soft-Switching Medium-Voltage DAB Converter With Series-Connected SiC MOSFETs

Accelerating Dynamic Aperture Evaluation Using Deep Neural Networks

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

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

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Understanding generalization and robustness in modern deep learning

Enhancement of Ultrafast Ultrasound Images: A Performance Comparison Between CNN Trained with RF or IQ Images

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Using Physical Dynamics: Accurate and Real-Time Object Detection for High-Resolution Video Streaming on Internet of Things Devices

Error estimates for SUPG-stabilised Dynamical Low Rank Approximations

Leveraging large language models for predictive chemistry

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms