Non-Structured DNN Weight Pruning--Is It Beneficial in Any Platform?

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.

The rapid evolution of Machine Learning (ML) workloads, particularly Deep Neural Networks (DNNs) and Transformer-based models, has intensified demands on computing architectures, highlighting the limitations of traditional von Neumann systems due to the me ...

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probab ...

The nematode Caenorhabditis elegans offers a uniquely tractable model for studying the relationships between neuronal activity, connectivity, and behavior. Despite its simplicity, key questions remain about how information flows through its nervous system ...

This paper introduces a distributed operational solution for integrated transmission-distribution (ITD) system management. A fundamental challenge in designing distributed approaches for AC optimal power flow (OPF) problems in ITD systems is the nonconvexi ...

In real-world speech data processing, the scarcity of annotated data and the abundance of unlabelled speech data present a significant challenge. To address this, we propose an efficient data selection pipeline for fine-tuning ASR models by generating pseu ...

Heating and cooling of buildings account for around 15% of all global energy consumption. In light of the ongoing energy transition, we aim to improve the efficiency of both in a European single-family house by using photovoltaic-thermal collectors with a ...

Metal ions are indispensable cofactors for many proteins and play crucial roles in numerous biological processes, yet the computational design of metalloproteins and the optimization of metal coordination sites poses significant challenges due to the comp ...

We investigate the training dynamics of two-layer neural networks when learning multi-index target functions. We focus on multi-pass gradient descent (GD) that reuses the batches multiple times and show that it significantly changes the conclusion about wh ...

While classical in many theoretical settings-and in particular in statistical physics-inspired works-the assumption of Gaussian i.i.d. input data is often perceived as a strong limitation in the context of statistics and machine learning. In this study, we ...

During the past two decades, a number of two-terminal switching devices have been demonstrated in the literature. They typically exhibit hysteric behavior in the current-to-voltage characteristics. These devices have often been also referred to as memristi ...

The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called workers). Beyond accuracy, the u ...

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization ...

Studying the intricacies of individual subjects' moods and cognitive processing over extended periods of time presents a formidable challenge in medicine. While much of systems neuroscience appropriately focuses on the link between neural circuit functions ...

Multi-object spectroscopic galaxy surveys typically make use of photometric and colour criteria to select their targets. That is not the case of Euclid, which will use the NISP slitless spectrograph to record spectra for every source over its field of view ...

As the applications of biometric recognition systems are increasing rapidly, there is a growing need to secure the sensitive data used within these systems. Considering privacy challenges in such systems, different biometric template protection (BTP) schem ...

Intelligent Fault Diagnosis (IFD) based on deep learning has proven to be an effective and flexible solution, attracting extensive research. Deep neural networks can learn rich representations from vast amounts of representative labeled data for various ap ...

The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private observation ...

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...

A robust capacitive multisensory readout system is presented in this article. The system consists of a few thousand lossy capacitive-based sensors that can be modeled as a parallel connection of sensor capacitor and undesirable leakage resistance. The real ...

PurposeIn this work we performed an imaged-based computational study of the systolic fluid dynamics in presence of mitral valve regurgitation (MVR). In particular, we compared healthy and different regurgitant scenarios with the aim of quantifying differen ...

Non-Structured DNN Weight Pruning--Is It Beneficial in Any Platform?

Chat with Graph Search

Stop Wasting your Cache! Bringing Machine Learning into Cache Computing

Global Group Fairness in Federated Learning via Function Tracking

Behaviorally Relevant Information Content in Interneuron Activity

Advancing Distributed AC Optimal Power Flow for Integrated Transmission-Distribution Systems

Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering

A multi-modal nocturnal radiative cooling and solar-assisted heating system with model predictive control

Engineering of stable and functional metalloproteins using evolutionary computation, deep learning and simulation

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Gaussian universality of perceptrons with random labels

In-Memory Sensing and Computing for Cancer Diagnostics: A Perspective Paper

Brief Announcement: A Case for Byzantine Machine Learning

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition

Ethological computational psychiatry: Challenges and opportunities

Euclid: Testing photometric selection of emission-line galaxy targets?

Measuring Linkability of Protected Biometric Templates Using Maximal Leakage

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis

Discovering Influencers in Opinion Formation Over Social Graphs

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Robust Analog Multisensory Array System for Lossy Capacitive Sensors Over Long Distances

An Image-Based Computational Fluid Dynamics Study of Mitral Regurgitation in Presence of Prolapse