Concept

Presentation layer

Related publications (143)

Non-volatile data storage medium and system

Martin Vetterli, Yves Bellouard, Ruben Ricca

A data storage medium (2) comprising a stacked plurality of layers (9), each layer composed of a layer material selected from a group comprising at least two different dielectric materials, adjacent layers being formed of different materials, and at least ...

2023

A hybrid Selective Laser Sintering based process for the additive manufacturing of architectured composites

Erwan Philippe Guenier

Additive Manufacturing also commonly referred as 3D printing has been given a lot of interest lately. Market is growing exponentially and the aim for obtaining more complex and ready-to use parts is emerging. All the 3D printing processes consist in buildi ...

EPFL2023

BamX: Rethinking Deployability in Architecture through Weaving

Mark Pauly, Stefana Parascho, Seiichi Eduardo Suzuki Erazo, Tian Chen, Yingying Ren

Deployable gridshells are a class of planar-to-spatial structures that achievea 3D curved geometry by inducing bending on a flat grid of elastic beams. However, theslender nature of these beams often conflicts with the structure’s load-bearing capacity.To ...

De Gruyter2023

Arrest Mechanisms of Buoyant Hydraulic Fractures

Brice Tanguy Alphonse Lecampion, Andreas Möri, Carlo Peruzzo, Dmitriy Garagash

Hydraulic fracturing (HF) treatments can form widespread fractures. Understanding their containment at depth is critical, given the positive buoyancy contrast between the fracturing fluid and the surrounding rock, promoting upward growth. We study arrest m ...

American Rock Mechanics Association (ARMA), OnePetro2023

Ferroelectric device or structure and a method for producing ferroelectric devices or structures

Tobias Kippenberg, Zelin Tan

The present invention concerns a method for producing at least one ferroelectric device or structure comprising the steps of providing at least one ferroelectric material or layer, or providing at least one ferroelectric material or layer to be patterned o ...

2023

Layer-Wise Learning Framework for Efficient DNN Deployment in Biomedical Wearable Systems

David Atienza Alonso, Amir Aminifar, Tomas Teijeiro Campo, Alireza Amirshahi, Saleh Baghersalimi

The development of low-power wearable systems requires specialized techniques to accommodate their unique requirements and constraints. While significant advancements have been made in the inference phase of artificial intelligence, the training phase rema ...

2023

, ,

Disclosed herein is a method for labelling a portion of a device, said method comprising the steps of providing a first substrate layer of a transparent or translucent material, depositing a first coloured material onto said first substrate layer in a labe ...

2022

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021

Method for flattening substrates or layers using 3d printing and etching

Niels Quack, Teodoro Graziosi, Nathanaël Restori

The present invention concerns a layer or substrate flattening method comprising the steps of: - providing a layer or substrate (1) to be flattened; - measuring a topography or surface profile of at least one area (3) of the layer or substrate to be flatte ...

2021

, , ,

Data lakes are complex ecosystems where heterogeneity prevails. Raw data of diverse formats are stored and processed, while long and expensive ETL processes are avoided. Apart from data heterogeneity, data lakes also entail hardware heterogeneity. Typical ...

2021

Graph Chatbot

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.

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021