Publication

Ex-ante measure of patent quality reveals intrinsic fitness for citation-network growth

Publications associées (29)

Learning Bollobas-Riordan Graphs Under Partial Observability

This work examines the problem of learning the topology of a network (graph learning) from the signals produced at a subset of the network nodes (partial observability). This challenging problem was recently tackled assuming that the topology is drawn acco ...

IEEE2021

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

Modeling of Stream Metabolism from Reach-scale to the Scale of Entire River Networks

Pier Luigi Segatto

Streams are key components of the global carbon (C) cycle. The river network conceptualization moved from the pipelineâ idea, in which C is solely transported, to the active ecosystemâ concept, in which both terrestrial derived and autochthonous C ...

EPFL2021

The Metabolic Regimes at the Scale of an Entire Stream Network Unveiled Through Sensor Data and Machine Learning

Enrico Bertuzzo, Tom Ian Battin, Pier Luigi Segatto

Streams and rivers form dense networks that drain the terrestrial landscape and are relevant for biodiversity dynamics, ecosystem functioning, and transport and transformation of carbon. Yet, resolving in both space and time gross primary production (GPP), ...

2021

An EEG-based methodology for the estimation of functional brain connectivity networks: Application to the analysis of newborn EEG seizure

Amir Hossein Omidvarnia

This study presents a new methodology for obtaining functional brain networks (FBNs) using multichannel scalp EEG recordings. The developed methodology extracts pair-wise phase synchrony between EEG electrodes to obtain FBNs at delta, theta, and alpha-band ...

ELSEVIER SCI LTD2021

The structural connectome and motor recovery after stroke: predicting natural recovery

Jean-Philippe Thiran, Philip Egger, Elena Beanato, Gabriel Girard, Friedhelm Christoph Hummel, Takuya Morishita, Maximilian Jonas Wessel, Philipp Johannes Koch, Giorgia Giulia Evangelista, Chang-Hyun Park

Stroke patients vary considerably in terms of outcomes: some patients present ‘natural’ recovery proportional to their initial impairment (fitters), while others do not (non-fitters). Thus, a key challenge in stroke rehabilitation is to identify individual ...

2021

The triangular value of patents

Albina Khairullina

This thesis addresses the question of a patent value from three different angles. It comprises three papers on the patent valuation methods. The patent valuation issues are well-known to the world of research and practice. However, the debates over what th ...

EPFL2020

Wanted: A standard for virtual patent marking

Gaétan Jean A de Rassenfosse, Kyle William Higham

Patent marking is used by patentees to provide a form of notice to the public about the existence of a patent and can increase damages awarded in cases of infringement. Historically, marking is done by listing the associated patents on the product they cov ...

OXFORD UNIV PRESS2020

Discrimination against foreigners in the U.S. patent system

Gaétan Jean A de Rassenfosse

Inventions of foreign origin are about ten percentage points less likely to be granted a U.S. patent than domestic inventions. An empirical analysis of 1.5 million U.S. patent applications identifies three systematic differences between foreign and domesti ...

2020

Publications associées (29)

Learning Bollobas-Riordan Graphs Under Partial Observability

Ali H. Sayed, Michele Cirillo

IEEE2021

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

Modeling of Stream Metabolism from Reach-scale to the Scale of Entire River Networks

Pier Luigi Segatto

EPFL2021

The Metabolic Regimes at the Scale of an Entire Stream Network Unveiled Through Sensor Data and Machine Learning

Enrico Bertuzzo, Tom Ian Battin, Pier Luigi Segatto

2021

An EEG-based methodology for the estimation of functional brain connectivity networks: Application to the analysis of newborn EEG seizure

Amir Hossein Omidvarnia

ELSEVIER SCI LTD2021