LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions

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 ability of the brain to produce adaptive and dexterous movements relies on the seamless integration of sensory feedback into motor commands. Despite significant advances in motor neuroscience, critical gaps persist in understanding how proprioceptive a ...

This paper presents a comprehensive framework for extracting georeferenced vehicle trajectories from high-altitude drone imagery, addressing key challenges in urban traffic monitoring and the limitations of traditional ground-based systems. Our approach in ...

Computational methods at the atomic scale based on machine learning have been a fruitful research field in the past decade by merging the advantages of classical and quantum mechanical approaches. While parts of the field are already reaching a mature stat ...

Semantic segmentation with deep learning plays a crucial role in various fields, including civil engineering, particularly in tasks such as damage assessment and urban planning. This paper addresses the challenge of efficiently training deep learning model ...

Recently, remarkable progress has been made in the application of machine learning (ML) techniques (e.g., neural networks) to transformer fault diagnosis. However, the diagnostic processes employed by these techniques often suffer from a lack of interpreta ...

Background: The interpretation of lung sounds plays a crucial role in the appropriate diagnosis and management of pediatric asthma. Applying artificial intelligence (AI) to this task has the potential to better standardize assessment and may even improve i ...

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes barely any progre ...

In recent years, numerical simulations of hemodynamics have gained significant attention within the medical community, thanks to their ability of non-invasively estimating the blood flow conditions. However, high-fidelity simulations require extensive comp ...

Over the past years, implantable closed-loop neural interfaces have received increasing attention for their potential to enhance the understanding of the brain, treat neurological disorders, and provide unprecedented opportunities for individuals with para ...

This paper presents a geometry-driven approach to form-finding with reused stock elements. Our proposed workflow uses a K-mean algorithm to cluster stock elements and incorporate their geometrical values early in the form-finding process. A feedback loop i ...

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction. As models get larger, more ubiquitous ...

Intense winds are a challenge for vertical take-off and landing drones with wings. In particular, in the hovering regime, wings are sensitive to wind currents that can be detrimental to their operational and energetic performances. Tail-sitters are particu ...

This paper proposes a computational approach to form-find pin-jointed bar structures subjected to combinations of tension and compression forces. The generated equilibrium states can meet structural and geometrical constraints via gradient-based optimizati ...

Convolutional neural networks, as most artificial neural networks, are frequently viewed as methods different in essence from kernel-based methods. In this work we translate several classical convolutional neural networks into kernel-based counterparts. Ea ...

Humans can rapidly estimate the statistical properties of groups of stimuli, including their average and variability. But recent studies of so-called Feature Distribution Learning (FDL) have shown that observers can quickly learn even more complex aspects ...

Advances in soft sensors coupled with machine learning are enabling increasingly capable wearable systems. Since hand motion in particular can convey useful information for developing intuitive interfaces, glove-based systems can have a significant impact ...

This thesis is centered on questions coming from Machine Learning (ML) and Statistical Field Theory (SFT). In Machine Learning, we consider the subfield of Supervised Learning (SL), and in particular regression tasks where one tries to find a regressor tha ...

Patient-Derived Xenografts (PDXs) are the preclinical models which best recapitulate inter- and intra-patient complexity of human breast malignancies, and are also emerging as useful tools to study the normal breast epithelium. However, data analysis gener ...

Generalised linear models for multi-class classification problems are one of the fundamental building blocks of modern machine learning tasks. In this manuscript, we characterise the learning of a mixture of K Gaussians with generic means and covariances v ...

Enabling autonomous driving (AD) can be considered one of the biggest challenges in today?s technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception is usu ...

LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions

Chat with Graph Search

Reverse engineering primate sensorimotor control with machine learning

Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery

Mathematical Analysis and Optimization of Features for Atomistic Machine Learning

Partial annotations in active learning for semantic segmentation

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Automated Interpretation of Lung Sounds by Deep Learning in Children With Asthma: Scoping Review and Strengths, Weaknesses, Opportunities, and Threats Analysis

Learning Time-Scales in Two-Layers Neural Networks

Reduced order models to address temporal complexity and geometrical variability in hemodynamics

Neurostimulation and Wireless Data Transmission Circuits for Implantable High-Density Neural Interfaces

Geometry-Driven Stock-Constrained Truss Design via Equilibrium-Based Structural Models

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations

Wind Defiant Morphing Drones

Constrained Form-Finding of Tension-Compression Structures using Automatic Differentiation

Revisiting Convolutional Neural Networks from the Viewpoint of Kernel-Based Methods

Feature distribution learning by passive exposure

A Wearable Smart Glove and Its Application of Pose and Gesture Detection to Sign Language Classification

Complex Analysis meets Statistical Mechanics: Applications to Kernel Methods and Conformal Field Theory

Deep Learning Enables Individual Xenograft Cell Classification in Histological Images by Analysis of Contextual Features

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions

The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing