Publications associées à Learning anisotropic filters on product graphs

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

EPFL2023

Transformer Models for Vision

Jean-Baptiste Francis Marie Juliette Cordonnier

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

EPFL2023

Equivariant Neural Architectures for Representing and Generating Graphs

Clément Arthur Yvon Vignac

Graph machine learning offers a powerful framework with natural applications in scientific fields such as chemistry, biology and material sciences. By representing data as a graph, we encode the prior knowledge that the data is composed of a set of entiti ...

EPFL2023

Estimating and Improving the Robustness of Attributions in Text

Ádám Dániel Ivánkay

End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...

EPFL2023

A multichannel versatile brain activity classification and closed loop neuromodulation system, device and method using a highly multiplexed mixed-signal front-end

Mahsa Shoaran, Uisub Shin, Bingzhao Zhu

A closed-loop neuromodulation system, including an electrode array that is implantable to a brain of a subject, analog front-end device (AFD) for selectively selecting and reading a plurality of channels from electrode array, a finite impulse response (FIR ...

2023

LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection

Jiancheng Yang, Bo Du, Rui Xu

Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection. However, existing CNN based pulmonary nodule detection methods lack the ability to capture long-range dependencies, which is vita ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

Learnable filter-banks for CNN-based audio applications

Nicolas Aspert, Benjamin Ricaud, Helena Peic Tukuljac, Laurent Colbois

We investigate the design of a convolutional layer where kernels are parameterized functions. This layer aims at being the input layer of convolutional neural networks for audio applications or applications involving time-series. The kernels are defined as ...

2022

Ultra-Small Bent Meta-Waveguide Filters

Romain Christophe Rémy Fleury, Maliheh Khatibi Moghaddam

This paper demonstrates the capability of locally resonant metamaterials (LRMs) for creating compact metallic waveguide E- and H-bends, which are simultaneously working as bandpass filters. For creating these bent meta-filters, we use composite pin-pipe wa ...

IEEE2022

Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering

Mathew Magimai Doss, Eklavya Sarkar

Voice activity detection (VAD) is an important pre-processing step for speech technology applications. The task consists of deriving segment boundaries of audio signals which contain voicing information. In recent years, it has been shown that voice source ...

ISCA2022

Ultra-Compact Ka-band Metamaterial Waveguide Filters, Fabricated by Lost-Wax Casting

Romain Christophe Rémy Fleury, Maliheh Khatibi Moghaddam

This paper proposes a novel technique for the design of miniaturized Ka-band filters based on locally resonant metamaterials (LRMs), which are fabricated monolithically using lost wax casting. We implement ultra-small metamaterial filters by exploiting a n ...

IEEE2021