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

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 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 ...

Foundation models are highly versatile neural-network architectures capable of processing different data types, such as text and images, and generalizing across various tasks like classification and generation. Inspired by this success, we propose Foundati ...

Machine learning models have made significant progress in load forecasting, but their forecast accuracy is limited in cases where historical load data is scarce. Inspired by the outstanding performance of large language models (LLMs) in computer vision and ...

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 ...

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 ...

This thesis investigates methods to construct more capable models more efficiently, focusing on two aspects: improved architectures and optimization. We examine principled architectural modifications that reduce computational costs or introduce features fo ...

Incorporating pixel contextual information is critical for accurate segmentation. In this paper, we show that an effective way to incorporate contextual information is through a patch-based classifier. This patch classifier is trained to identify classes p ...

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 ...

Genetic variation plays a crucial role in human disease susceptibility and molecular pathophysiology. This thesis explores genetic determinants of disease using advanced computational approaches, including statistical modeling, network analysis, and deep l ...

Advances in generative models increase the need for sample quality assessment. To do so, previous methods rely on a pre-trained feature extractor to embed the generated samples and real samples into a common space for comparison. However, different feature ...

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some computationally-bounded nodes may not ...

Climate change has led to stronger warming in the Arctic, causing higher ground temperatures and extensive permafrost thaw. Retrogressive Thaw Slumps (RTSs) represent one of the most rapid and considerable geomorphological changes in permafrost regions, oc ...

The growing deployment of low-cost, distributed sensor networks in environmental and biomedical domains has enabled continuous, large-scale health monitoring. However, these systems often face challenges related to degraded data quality caused by sensor dr ...

Wireless sensing offers an alternative to wearables for contactless monitoring of human activity and vital signs. However, most existing systems use bistatic setups, which suffer from phase imperfections due to unsynchronized clocks. Monostatic systems ove ...

We introduce an ensemble learning method for dynamic portfolio valuation and risk management building on regression trees. We learn the dynamic value process of a derivative portfolio from a finite sample of its cumulative cash flow. The estimator is given ...

Interactive robotics is increasingly used to investigate animal behaviour, including communication, mating and collective dynamics. An essential component for such systems is sensing the animals and the relevant aspects of the habitat to enable coherent cl ...

Differential privacy provides a robust framework for protecting sensitive data, while maintaining its utility for computation. In essence, a differentially private algorithm takes as input the data of multiple parties, and returns an output disclosing mini ...

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 ...

Auditory research aims in general to lead to understanding of physiological processes. By contrast, the state of the art in automatic speech processing (notably recognition) is dominated by large pre-trained models that are meant to be used as black-boxes. ...

Goal: In patients with coronary artery disease, the prediction of future cardiac events such as myocardial infarction (MI) remains a major challenge. In this work, we propose a novel anatomy-informed multimodal deep learning framework to predict future MI ...

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

Chat with Graph Search

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

Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians

TimeGPT in load forecasting: A large time series model perspective

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

Musculoskeletal motor control with reinforcement learning

Enhanced Architectures and Optimization Methods for Efficient Language Modeling

Beyond Pixels: Semi-supervised Semantic Segmentation with a Multi-scale Patch-Based Multi-label Classifier

Teaching oxidation states to neural networks

Learning the language of the genome: AI- and data-driven decoding of genetic variants and disease mechanisms

Assessing Sample Quality via the Latent Space of Generative Models

Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence

Detecting mass wasting of Retrogressive Thaw Slumps in spaceborne elevation models using deep learning

Efficient Unsupervised Domain Adaptation Regression for Spatial-Temporal Sensor Fusion

An SDR-Based Monostatic Wi-Fi System with Analog Self-Interference Cancellation for Sensing

Ensemble learning for portfolio valuation and risk management

Extending Sensory Capabilities of a Biohybrid System: Prediction of Honeycomb Fill

Quantum Differential Privacy in the Local Model

Topics in statistical physics of high-dimensional machine learning

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

Anatomy-Informed Multimodal Learning for Myocardial Infarction Prediction