Publications associées à Noyau polynomial

End-to-end kernel learning via generative random Fourier features

Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learn-ing an optimal feature map is often formulated as a ...

ELSEVIER SCI LTD2023

Kernel Methods and Similarity Learning Applied in Computational Chemistry

Raimon Fabregat I De Aguilar-Amat

Over the last two decades, data-powered machine learning (ML) tools have profoundly transformed numerous scientific fields. In computational chemistry, machine learning applications have permitted faster predictions of chemical properties and provided powe ...

EPFL2022

Oblivious Sketching of High-Degree Polynomial Kernels

Mikhail Kapralov, Amir Zandieh

Kernel methods are fundamental tools in machine learning that allow detection of non-linear dependencies between data without explicitly constructing feature vectors in high dimensional spaces. A major disadvantage of kernel methods is their poor scalabili ...

ASSOC COMPUTING MACHINERY2020

Fourier Sampling in Signal Processing and Numerical Linear Algebra

Amir Zandieh

This thesis focuses on developing efficient algorithmic tools for processing large datasets. In many modern data analysis tasks, the sheer volume of available datasets far outstrips our abilities to process them. This scenario commonly arises in tasks incl ...

EPFL2020

A novel biomechanical approach for animal behaviour recognition using accelerometers

Kamiar Aminian, Pritish Chakravarty

Data from animal-borne inertial sensors are widely used to investigate several aspects of an animal's life, such as energy expenditure, daily activity patterns and behaviour. Accelerometer data used in conjunction with machine learning algorithms have b ...

2019

A Sampling Theory for Non-Decaying Signals

Michaël Unser, Quy Ha Nguyen

The classical assumption in sampling and spline theories is that the input signal is square-integrable, which prevents us from applying such techniques to signals that do not decay or even grow at infinity. In this paper, we develop a sampling theory for m ...

2017

Sampling and Reconstruction of Shapes with Algebraic Boundaries

Martin Vetterli, Arash Amini, Mitra Fatemi

We present a sampling theory for a class of binary images with finite rate of innovation (FRI). Every image in our model is the restriction of

\mathds{1}_{\{p\leq0\}}

to the image plane, where

\mathds{1}

denotes the indicator function and

p

is some r ...

2016

Word pair classification during imagined speech using direct brain recordings

José del Rocio Millán Ruiz, Inaki Asier Iturrate Gil, Stéphanie Martin

People that cannot communicate due to neurological disorders would benefit from an internal speech decoder. Here, we showed the ability to classify individual words during imagined speech from electrocorticographic signals. In a word imagery task, we used ...

Nature Research2016

Some Developments of the Cooray–Rubinstein Formula in the Time Domain

Farhad Rachidi-Haeri

A rigorous formula representing the counterpart of the Cooray-Rubinstein expression in the time domain has recently been derived by the authors. In this paper, the formula is particularized for the cases of a unit step and a linearly rising channel-base cu ...

Institute of Electrical and Electronics Engineers2015

Accurate band gaps of extended systems via efficient vertex corrections in GW

Alfredo Pasquarello, Wei Chen

We propose the use of an approximate bootstrap exchange-correlation kernel to account for vertex corrections in self-consistent GW calculations. We show that the approximate kernel gives accurate band gaps for a variety of extended systems, including simpl ...

2015