Fixed point geometry in chaotic neural networks

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.

Traditional aerodynamic shape optimization (ASO) is costly and time-intensive, requiring extensive manual tuning for parameterization to define the design space and manipulate geometries. Conventional parameterization methods limit flexibility and demand s ...

When two objects are rubbed together, they create friction, heat, and their surfaces might be worn away. However, the fundamental mechanisms behind these processes remain poorly understood. While empirical engineering models exist, they are tailored to spe ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

Wind energy potential in complex terrain is still poorly understood and difficult to quantify. With Switzerland’s current efforts to shift to renewable energy resources, it is now becoming even more crucial to investigate the hidden potential of wind energ ...

Censuses are structured documents of great value for social and demographic history, which became widespread from the nineteenth century on. However, the plurality of formats and the natural variability of historical data make their extraction arduous and ...

Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than others. This causes traditional eva ...

Deep learning (DL) has been wildly successful in practice, and most of the state-of-the-art machine learning methods are based on neural networks (NNs). Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of ...

This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to ...

Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While novel denoising networks were designed for real images coming from different distributions, or for sp ...

The use of radar for precipitation measurement in mountainous regions is complicated by many factors, especially beam shielding by terrain features, which, for example, reduces the visibility of the shallow precipitation systems during the cold season. Whe ...

Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and high-resolution image datasets is still an open challenge, due to memory an ...

Fixed point geometry in chaotic neural networks

Chat with Graph Search

Automated Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Wear across scales

Towards Trustworthy Deep Learning for Image Reconstruction

Combining Weather Station Data and Short-Term LiDAR Deployment to Estimate Wind Energy Potential with Machine Learning: A Case Study from the Swiss Alps

An end-to-end pipeline for historical censuses processing

Neural and algorithmic bases of odor guided trail following in mice

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

Deep Learning Meets Sparse Regularization

Network Classifiers Based On Social Learning

Deep Gaussian denoiser epistemic uncertainty and decoupled dual-attention fusion

Learning about the vertical structure of radar reflectivity using hydrometeor classes and neural networks in the Swiss Alps

DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction