Overflow-free Compute Memories for Edge AI Acceleration

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.

Atomistic machine learning has revolutionized atomistic modeling. Traditionally, molecular dynamics simulations relied on classical force fields or electronic structure calculations like Density Functional Theory. Classical force fields are fast but less p ...

Federated Learning (FL) enables end-user devices to collaboratively train ML models without sharing raw data, thereby preserving data privacy. In FL, a central parameter server coordinates the learning process by iteratively aggregating the trained models ...

Living systems are commonly engineered through an iterative design-build-test process. However, unlike in other engineering disciplines, the systems that synthetic biologists construct are able to evolve. On the one hand, this compromises their long-term s ...

The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high gen ...

Traditional example-based learning methods are often limited by static, expert-created content. Hence, they face challenges in scalability, engagement, and effectiveness, as some learners might struggle to relate to the examples or find them relevant. To a ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

We present the identification of the non-linear dynamics of a novel hovercraft design, employing end-to-end deep learning techniques. Our experimental setup consists of a hovercraft propelled by racing drone propellers mounted on a lightweight foam base, a ...

Modern automobiles are equipped with advanced computing capabilities, allowing them to become powerful computing units capable of processing a large amount of data and training machine learning models. However, machine learning algorithms typically require ...

Endogenous and exogenous uncertainties exert significant influences on energy planning. In this study, we propose a systematic methodology to excavate the uncertainty space, by combining mix-integer linear programming (MILP), Monte Carlo simulation, and ma ...

We consider the problem of sharing a set of indivisible goods among agents in a fair manner, namely such that the allocation is envy-free up to any good (EFX). We focus on the problem of computing an EFX allocation in the two-agent case and characterize th ...

Most of our lives are conducted in the cyberspace. The human notion of privacy translates into a cyber notion of privacy on many functions that take place in the cyberspace. This article focuses on three such functions: how to privately retrieve informatio ...

Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as distributed SGD, in a way that guarantees convergence despite the presence ...

It was recently shown that almost all solutions in the symmetric binary perceptron are isolated, even at low constraint densities, suggesting that finding typical solutions is hard. In contrast, some algorithms have been shown empirically to succeed in fin ...

We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function. When the system is linear and the cost is convex, the System Level Synthesis (SLS) approach offers an effe ...

How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson-Lindenstrauss lemma answers this question for linear fully-connected neural networks (FNNs), stat ...

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the b ...

In the literature, the task of dysarthric speech intelligibility assessment has been approached through development of different low-level feature representations, subspace modeling, phone confidence estimation or measurement of automatic speech recognitio ...

Air traffic management and specifically air-traffic control (ATC) rely mostly on voice communications between Air Traffic Controllers (ATCos) and pilots. In most cases, these voice communications follow a well-defined grammar that could be leveraged in Aut ...

Mixed logit models with unobserved inter-and intra-individual heterogeneity hierarchically extend standard mixed logit models by allowing tastes to vary randomly both across individuals and across choice situations encountered by the same individual. Recen ...

Overflow-free Compute Memories for Edge AI Acceleration

Chat with Graph Search

Advancing understanding and practical performance of machine learning interatomic potentials

Practical Federated Learning without a Server

Light-directed evolution of dynamic biological systems

CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction

GELEX: Generative AI-Hybrid System for Example-Based Learning

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

On identifying the non-linear dynamics of a hovercraft using an end-to-end deep learning approach

Hierarchical Federated Learning in MEC Networks with Knowledge Distillation

Deep excavation of the impact from endogenous and exogenous uncertainties on long-term energy planning

The Frontier of Intractability for EFX with Two Agents

Private Retrieval, Computing, and Learning: Recent Progress and Future Challenges

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums

Binary Perceptron: Efficient Algorithms Can Find Solutions in a RareWell-Connected Cluster

Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems

A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss

Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features

Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems

Evaluating the predictive abilities of mixed logit models with unobserved inter- and intra-individual heterogeneity