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 thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

A frequency scaling governor is critical for the performance management of cloud servers, as it enhances energy efficiency and helps to control operational temperatures, thereby ensuring system reliability. However, our in-depth analysis of the application ...

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accurac ...

Mitigating the energy requirements of artificial intelligence requires novel physical substrates for computation. Phononic metamaterials have vanishingly low power dissipation and hence are a prime candidate for green, always-on computers. However, their u ...

Embedded memories occupy an increasingly dominant part of the area and power budgets of modern systems-on-chips (SoCs). Multi-ported embedded memories, commonly used by media SoCs and graphical processing units, occupy even more area and consume higher pow ...

Machine learning and artificial intelligence methods have achieved remarkable success, matching and even surpassing human capabilities in various complex tasks. However, many demonstrations have generally neglected a critical part of the intelligence that ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

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 ...

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...

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 ...

In two-stage solid-state transformers with input-series output-parallel structure, the LLC converter operating at a fixed switching frequency is a common choice for the isolated DC/DC conversion stage because it can provide a high efficiency and a fixed vo ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

A search is presented for the pair production of new heavy resonances, each decaying into a top quark (t) or antiquark and a gluon (g). The analysis uses data recorded with the CMS detector from proton-proton collisions at a center-of-mass energy of 13 TeV ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

The versatility of half-bridge configuration of silicon carbide (SiC) metal-oxide-semiconductor field-effect transistor (MOSFET) power module contributes to its widespread adoption, highlighting the popularity and significance of its corresponding dual gat ...

As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. However, centralized training, the most common paradigm for MARL, limits large-scale deployment i ...

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

Chat with Graph Search

Learning to Reason with Neural Networks: Principles and Methods

Is the powersave governor really saving power?

A comparative analysis of gene expression profiling by statistical and machine learning approaches

Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy

In-Sensor Passive Speech Classification with Phononic Metamaterials

Multi-Ported GC-eDRAM Bitcell with Dynamic Port Configuration and Refresh Mechanism

Sequential Reasoning with Socially Caused Beliefs

Computational design of complex protein folds and soluble analogs of membrane proteins

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

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

Ripple Voltage and Loss Reduction of Single-Phase ISOP SST by Eliminating the Second Harmonic Current in LLC Converters

Safe Deep Neural Networks

Search for Pair Production of Heavy Particles Decaying to a Top Quark and a Gluon in the Lepton Plus Jets Final State in Proton-proton Collisions at √s=13 Tev

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Active Voltage Balancing with Seamless Integration into Dual Gate Driver for Series Connection of SiC MOSFETs

Scalable Multi-agent Reinforcement Learning for Residential Load Scheduling Under Data Governance