Get More for Less in Decentralized Learning Systems

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.

Humans and animals both use acoustic signals for vocal communication. The advent of self-supervised learning (SSL) has enabled neural networks to learn robust and general feature representations through the intrinsic acoustic structure of input signals, wi ...

Triboelectric nanogenerators (TENGs) serve as a key technology in flexible electronic devices, especially tactile sensors, enabling flexible robotic manipulators to effectively interact with their external environment. Persistent challenges include inadequ ...

The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation lear ...

Animals, including humans, interact with the external environment primarily through motion. Replicating their motor control skills in artificial embodied agents is a major objective of artificial intelligence research. This thesis presents a collection of ...

While the accurate description of redox reactions remains a challenge for first-principles calculations, it has been shown that extended Hubbard functionals (DFT+U+V) can provide a reliable approach, mitigating self-interaction errors, in materials with st ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

The auditory system allows the estimation of the distance to sound-emitting objects using multiple spatial cues. In virtual acoustics over headphones, a prerequisite to render auditory distance impression is sound externalization, which denotes the percept ...

Inner ear imaging is important for the assessment of hearing disorders. A major cause of hearing loss is the damage to the sensory hair cells, which are located inside the cochlea, a spiral-shaped bone in the inner ear. Imaging of intracochear hair cells i ...

Hearing Loss (HL) is the most prevalent sensorineural disorder, affecting 360 million people worldwide. As genetic causes lead to 50% of pre-lingual deafness, gene therapy is considered as a potential therapeutic strategy. Mutations in the TMC1 gene are li ...

Animal social networks are shaped by multiple selection pressures, including the need to ensure efficient communication and functioning while simultaneously limiting disease transmission. Social animals could potentially further reduce epidemic risk by alt ...

Displaced communication, whereby individuals communicate regarding a subject that is not immediately present (spatially or temporally), is one of the key features of human language. It also occurs in a few animal species, most notably the honeybee, where t ...

The application of unsupervised domain adaptation (UDA)-based fault diagnosis methods has shown significant efficacy in industrial settings, facilitating the transfer of operational experience and fault signatures between different operating conditions, di ...

Following up a two-day invitation-only expert workshop in Geneva on the subject of Trust and Precision Medicine, IRGC published a workshop report in April 2018. This report addresses the concept of trust and conditions of trustworthiness in each of the thr ...

Humans can express their actions and intentions, resorting to verbal and/or non-verbal communication. In verbal communication, humans use language to express, in structured linguistic terms, the desired action they wish to perform. Non-verbal communication ...

Little is known about the perception of artificial spatial hearing by hearing-impaired subjects. The purpose of this study was to investigate how listeners with hearing disorders perceived the effect of a spatialization feature designed for wireless microp ...

Phonological classes define articulatory-free and articulatory-bound phone attributes. Deep neural network is used to estimate the probability of phonological classes from the speech signal. In theory, a unique combination of phone attributes form a phonem ...

Rectified-linear-unit (ReLU) neural networks, which play a prominent role in deep learning, generate continuous and piecewise-linear (CPWL) functions. While they provide a powerful parametric representation, the mapping between the parameter and function s ...

Animal models of hearing loss and tinnitus observe pathological neural activity in the tonotopic frequency maps of the primary auditory cortex. Here, we applied ultra high-field fMRI at 7 T to test whether human patients with unilateral hearing loss and ti ...

Two-dimensional (2D) materials have been a central focus of recent research because they host a variety of properties, making them attractive both for fundamental science and for applications. It is thus crucial to be able to identify accurately and effici ...

A remote microphone (RM) system can be used in combination with wearable binaural communication devices, such as hearing aids (HAs), to improve speech intelligibility. Typically, a speaker is equipped with a body-worn microphone which enables to pick up th ...

Get More for Less in Decentralized Learning Systems

Chat with Graph Search

Transferability of Learnt Speech Representations for Decoding Non-Human Vocal Communication

Intelligent Soft Robotic System for Sensing and Recognition via Triboelectric‐Based Multi‐Sensor Fusion

MARBLE: interpretable representations of neural population dynamics using geometric deep learning

Musculoskeletal motor control with reinforcement learning

Teaching oxidation states to neural networks

Topics in statistical physics of high-dimensional machine learning

Perception of Auditory Distance in Normal-Hearing and Moderate-to-Profound Hearing-Impaired Listeners

Inner ear cellular imaging through scattering bone

Delivery of CRISPR/Cas9 using AAV-PHP.B in the inner ear leads to allele-specific inactivation of the mutated Tmc1 allele and protects auditory function in Beethoven mice

Social network plasticity decreases disease transmission in a eusocial insect

The evolution of behavioral cues and signaling in displaced communication

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

Governance of Trust in Precision Medicine

Non-verbal Communication between Humans and Robots: Imitation, Mutual Understanding and Inferring Object Properties

Effects of Binaural Spatialization in Wireless Microphone Systems for Hearing Aids on Normal-Hearing and Hearing-Impaired Listeners

Perceptual Information Loss due to Impaired Speech Production

Stable parameterization of continuous and piecewise-linear functions

High-Resolution fMRI of Auditory Cortical Map Changes in Unilateral Hearing Loss and Tinnitus

Machine-learning accelerated identification of exfoliable two-dimensional materials

Auditory externalization of a remote microphone signal