From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

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.

Early work has found that large language models (LLMs) can generate persuasive content. However, evidence on whether they can also personalize arguments to individual attributes remains limited, despite being crucial for assessing misuse. This preregistere ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

As the demand for high channel counts and high-resolution recordings of neural activity continues to grow, the increased power and data rate generated impose hard constraints on the telemetry capabilities of wireless implantable neural interfaces. To addre ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Photorealistic synthetic data and novel rendering techniques significantly advanced computer vision research. However, datasets focused on computer vision applications cannot be easily applied to robotics because they typically lack physics-related informa ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

Given a ground-level query image and a geo-referenced aerial image that covers the query’s local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works have focused on dev ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relev ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcrib ...

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

Slope deformation poses significant risks to infrastructure, ecosystems, and human safety, making early and accurate predictions essential for mitigating slope failures and landslides. In this study, we propose a novel approach that integrates a fractional ...

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous w ...

Synthesizability in generative molecular design remains a pressing challenge. Existing methods to assess synthesizability include heuristics-based metrics or retrosynthesis models which predict a synthetic pathway. By contrast, an explicit approach anchors ...

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

Image steganalysis, detecting hidden data in digital images, is essential for enhancing digital security. Traditional steganalysis methods typically rely on large, pre-labeled image datasets, which are difficult and costly to compile. To address this, this ...

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

The Birman-Williams theorem gives a connection between the collection of unstable periodic orbits (UPOs) contained within a chaotic attractor and the topology of that attractor, for three-dimensional systems. In certain cases, the fractal dimension of a ch ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

Chat with Graph Search

On the conversational persuasiveness of GPT-4

Partial discharge localization in power transformer tanks using machine learning methods

A Reconfigurable High-Dynamic Range ∆Σ Front-End with Event-Based Decimation for Bandwidth-Efficient Implantable Neural Interfaces

Robust machine learning for neuroscientific inference

GRADE: Generating Realistic and Dynamic Environments for robotics research with Isaac Sim

Enabling Uncertainty Estimation in Iterative Neural Networks

Adapting Fine-Grained Cross-View Localization to Areas Without Fine Ground Truth

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Integer Linear Programming for Unsupervised Training Set Selection in Molecular Machine Learning

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

Slope Deformation Prediction Combining Particle Swarm Optimization-Based Fractional-Order Grey Model and K-Means Clustering

Network time series forecasting in photovoltaics power production

Directly optimizing for synthesizability in generative molecular design using retrosynthesis models

On the number of regions of piecewise linear neural networks

Image steganalysis using active learning and hyperparameter optimization

Residual-based attention in physics-informed neural networks

The topology of a chaotic attractor in the Kuramoto-Sivashinsky equation

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models