18 citations · 40 across the 9 of their papers we have counts for
9 papers
Polynomial, trigonometric, and tropical activations
Ismail Khalfaoui-Hassani, Stefan Kesselheim
Which functions can be used as activations in deep neural networks? This article explores families of functions based on orthonormal bases, including the Hermite polynomial basis a…
Dilated Convolution with Learnable Spacings
Ismail Khalfaoui-Hassani
This thesis presents and evaluates the Dilated Convolution with Learnable Spacings (DCLS) method. Through various supervised learning experiments in the fields of computer vision,…
Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study
Rabih Chamas, Ismail Khalfaoui-Hassani, Timothee Masquelier
Dilated Convolution with Learnable Spacing (DCLS) is a recent advanced convolution method that allows enlarging the receptive fields (RF) without increasing the number of parameter…
Audio classification with Dilated Convolution with Learnable Spacings
Ismail Khalfaoui-Hassani, Timothée Masquelier, Thomas Pellegrini
Dilated convolution with learnable spacings (DCLS) is a recent convolution method in which the positions of the kernel elements are learned throughout training by backpropagation.…
Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
Ilyass Hammouamri, Ismail Khalfaoui-Hassani, Timothée Masquelier
Spiking Neural Networks (SNNs) are a promising research direction for building power-efficient information processing systems, especially for temporal tasks such as speech recognit…
Adapting a ConvNeXt model to audio classification on AudioSet
Thomas Pellegrini, Ismail Khalfaoui-Hassani, Etienne Labbé +1
In computer vision, convolutional neural networks (CNN) such as ConvNeXt, have been able to surpass state-of-the-art transformers, partly thanks to depthwise separable convolutions…
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or…
Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing
Alireza Azadbakht, Saeed Reza Kheradpisheh, Ismail Khalfaoui-Hassani +1
Deep convolutional neural networks (DCNNs) have become the state-of-the-art (SOTA) approach for many computer vision tasks: image classification, object detection, semantic segment…
Dilated convolution with learnable spacings
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
Recent works indicate that convolutional neural networks (CNN) need large receptive fields (RF) to compete with visual transformers and their attention mechanism. In CNNs, RFs can…