Dynamic Probabilistic Pruning: A General Framework for Hardware-Constrained Pruning at Different Granularities

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 escalating demands of artificial intelligence have underscored the limitations of traditional electronic computing, particularly in terms of power consumption and scalability. Optical computing offers a promising alternative, providing advantages in sp ...

Semi-structured networks (SSNs) merge the structures familiar from additive models with deep neural networks, allowing the modeling of interpretable partial feature effects while capturing higher-order non-linearities at the same time. A significant challe ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging w ...

Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning frameworks ...

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific domain has relied on ...

Federated Learning (FL) has gained considerable attention recently, as it allows clients to cooperatively train a global machine learning model without sharing raw data. However, its performance can be compromised due to the high heterogeneity in clients' ...

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 ...

Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learn-ing an optimal feature map is often formulated as a ...

Information theory has allowed us to determine the fundamental limit of various communication and algorithmic problems, e.g., the channel coding problem, the compression problem, and the hypothesis testing problem. In this work, we revisit the assumptions ...

Information derived from experiences is incorporated into the brain as changes to ensembles of cells, termed engram cells, which allow memory storage and recall. The mechanism by which those changes hold specific information is unclear. Here, we test the h ...

Extracting maximal information from experimental data requires access to the likelihood function, which however is never directly available for complex experiments like those performed at high energy colliders. Theoretical predictions are obtained in this ...

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

Virtual Memory (VM) is a critical programming abstraction that is widely used in various modern computing platforms. With the rise of datacenter computing and birth of planet-scale online services, the semantic and capacity requirements from memory have ev ...

Monitoring the cracks in walls, roads and other types of infrastructure is essential to ensure the safety of a structure, and plays an important role in structural health monitoring. Automatic visual inspection allows an efficient, costeffective and safe h ...

In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...

The management of existing civil infrastructure is becoming more crucial as a large share of bridges is approaching their theoretical end of service duration. Structural performance monitoring aims to verify bridge safety at a given time, and it should be ...

The Gm/ID approach has proven to be an efficient technique for the design of low-power analog circuits even in advanced technology nodes. It has already been shown that the normalized Gm/ID is actually a universal figure-of-merit (FoM) that is independent ...

Laser Powder Bed Fusion (LPBF) is an Additive Manufacturing (AM) process consolidating parts layer by layer, from a metallic powder bed. It allows no limitation in terms of geometry and is therefore of particular interest to various industries. Metallic LP ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

Dynamic Probabilistic Pruning: A General Framework for Hardware-Constrained Pruning at Different Granularities

Chat with Graph Search

Programming Nonlinear Computation with Nonlinear and Linear Optics

A Functional Extension of Semi-Structured Networks

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks

Multilingual Vision-Language Pre-training for the Remote Sensing Domain

Rethinking Personalized Client Collaboration in Federated Learning

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

End-to-end kernel learning via generative random Fourier features

On Speed and Advantage : Results in Information Velocity and Monitoring Problems

Engram cell connectivity as a mechanism for information encoding and memory function

Boosting likelihood learning with event reweighting

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

Rebooting Virtual Memory with Midgard

Segmenting Without Annotating: Crack Segmentation and Monitoring via Post-Hoc Classifier Explanations

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

Framework to evaluate the value of monitoring-technique information for structural performance monitoring

Design of Cryo-CMOS Analog Circuits using the Gm/ID Approach

Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions

Robust Collaborative Learning with Linear Gradient Overhead