Publications associées à How Far Can a 1-Pixel Camera Go? Solving Vision Tasks Using Photoreceptors and Computationally Designed Visual Morphology

Publications associées (17)

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

2025

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Thomas Grégoire Stegmüller

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

EPFL2025

FADE-CTP: A Framework for the Analysis and Design of Educational Computational Thinking Problems

Alberto Piatti, Francesco Mondada, Engin Walter Bumbacher

In recent years, the emphasis on computational thinking (CT) has intensified as an effect of accelerated digitalisation. While most researchers are concentrating on defining CT and developing tools for its instruction and assessment, we focus on the charac ...

Springer Science and Business Media LLC2025

S-R2D2: a spherical extension of the R2D2 deep neural network series paradigm for wide-field radio-interferometric imaging

Ayoub Tajja, Jean-Philippe Thiran, Jean-Paul Richard Kneib, Emma Elizabeth Tolley

Recently, the R2D2 paradigm, standing for ‘Residual-to-Residual DNN series for high-Dynamic-range imaging’, was introduced for image formation in Radio Interferometry (RI) as a learned version of the traditional algorithm CLEAN. The first incarnations of R ...

Oxford University Press (OUP)2025

A Systematic Design Flow for Compact and Efficient Analog Front-Ends in Closed-Loop Neuromodulation Systems

Mahsa Shoaran

In the growing field of closed-loop neuromodulation, designing power-and area-efficient analog front-ends (AFEs) for neural recording poses a significant challenge. Thus, an effective design flow is needed to ensure system's hardware efficiency and to auto ...

IEEE2024

Spatial Modeling for Building Design Evaluation: from Visual Landscape Quality Assessment to Devaluation Risk Estimation

Adam Robert Swietek

Zoning reform is a crucial tool for cities to adapt to contemporary challenges. However, its implementation remains challenging. Property owners, with a vested interest in the value of their neighborhoods, are sensitive to local developments and the potent ...

EPFL2024

Design of ultra-lightweight and energy-efficient civil structures through shape morphing

Gennaro Senatore, Arka Prabhata Reksowardojo

This paper gives a new formulation to synthesize load-responsive structures through shape morphing. The design method is based on the minimization of the whole-life energy, which comprises an embodied share in the material and an operational share for adap ...

Pergamon-Elsevier Science Ltd2023

Beyond worst-case analysis, with or without predictions

Andreas Maggiori

In this thesis we design online combinatorial optimization algorithms for beyond worst-case analysis settings. In the first part, we discuss the online matching problem and prove that, in the edge arrival model, no online algorithm can achieve a competiti ...

EPFL2023

Fast Parallel Algorithms for Enumeration of Simple, Temporal, and Hop-Constrained Cycles

Paolo Ienne, Kubilay Atasu, Jovan Blanusa

Finding cycles in directed graphs enables important applications in various domains such as finance, biology, chemistry, and network science. However, as the size of graph datasets continues to grow, it becomes increasingly difficult to discover cycles wit ...

arXiv2023

The Pixel Luminosity Telescope: a detector for luminosity measurement at CMS using silicon pixel sensors

Alexis Kalogeropoulos, Joanna Malgorzata Wanczyk, André Donadon Servelle

The Pixel Luminosity Telescope is a silicon pixel detector dedicated to luminosity measurement at the CMS experiment at the LHC. It is located approximately 1.75 m from the interaction point and arranged into 16 "telescopes", with eight telescopes installe ...

2023

Performance of the local reconstruction algorithms for the CMS hadron calorimeter with Run 2 data

Jan Steggemann, Konstantin Androsov, Anna Mascellani

A description is presented of the algorithms used to reconstruct energy deposited in the CMS hadron calorimeter during Run 2 (2015-2018) of the LHC. During Run 2, the characteristic bunch-crossing spacing for proton-proton collisions was 25 ns, which resul ...

Iop Publishing Ltd2023

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

Chen Liu

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning. However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...

EPFL2022

Putting ridesharing to the test: efficient and scalable solutions and the power of dynamic vehicle relocation

Boi Faltings, Panayiotis Danassis, Marija Sakota

We study the optimization of large-scale, real-time ridesharing systems and propose a modular design methodology, Component Algorithms for Ridesharing (CAR). We evaluate a diverse set of CARs (14 in total), focusing on the key algorithmic components of rid ...

SPRINGER2022

Industrial ontologies for interoperability in agile and resilient manufacturing

Dimitrios Kyritsis, Foivos Psarommatis Giannakopoulos

Ontologies provide an opportunity to tackle the interoperability challenge in digital manufacturing. Although ontologies have been used in numerous industrial projects, the problem of semantic interoperability in the industry is still unresolved. One reaso ...

TAYLOR & FRANCIS LTD2022

Computational Design of High-level Interlocking Puzzles

Ziqi Wang

Interlocking puzzles are intriguing geometric games where the puzzle pieces are held together based on their geometric arrangement, preventing the puzzle from falling apart. High-level-of-difficulty, or simply high-level, interlocking puzzles are a subclas ...

2022

U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search

Pascal Frossard, Ahmet Caner Yüzügüler, Nikolaos Dimitriadis

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

DIC Challenge 2.0: Developing Images and Guidelines for Evaluating Accuracy and Resolution of 2D Analyses

Edward Carlo Giorgio Andò

Background The DIC Challenge 2.0 follows on from the work accomplished in the first Digital Image Correlation (DIC) Challenge Reu et al. (Experimental Mechanics 58(7):1067, 1). The second challenge was required to better quantify the spatial resolution of ...

2022