Personal information

Activities

Collapse all

Employment (2)

Forschungszentrum Jülich: Jülich, DE

2024-07 to present | Postdoctoral Researcher (Jülich Supercomputing Center)
Employment
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Université de Toulouse: Toulouse, FR

2020-11-02 to 2024-03-31 | PhD student (MITT)
Employment
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Works (9)

Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study

arXiv preprint arXiv:2408.03164
2024 | Conference paper
Contributors: Chamas, Rabih; Khalfaoui-Hassani, Ismail; Masquelier, Timothee
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Learning delays in spiking neural networks using dilated convolutions with learnable spacings

ICLR 2024. The Twelfth International Conference on Learning Representations
2024 | Conference paper
Contributors: Hammouamri, Ilyass; Khalfaoui-Hassani, Ismail; Masquelier, Timothée
Source: Self-asserted source
Ismail Khalfaoui-Hassani

PhD Thesis: Dilated convolution with learnable spacings

2024 | Dissertation or Thesis
Contributors: Khalfaoui-Hassani, Ismail
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Audio classification with Dilated Convolution with Learnable Spacings

NeurIPS 2023 Workshop on Machine Learning for Audio
2023 | Conference paper
Contributors: Khalfaoui-Hassani, Ismail; Masquelier, Timothée; Pellegrini, Thomas
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Dilated convolution with learnable spacings

ICLR 2023. The Eleventh International Conference on Learning Representations
2023 | Conference paper
Contributors: Khalfaoui-Hassani, Ismail; Pellegrini, Thomas; Masquelier, Timothée
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Dilated Convolution with Learnable Spacings: beyond bilinear interpolation

ICML 2023. Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators
2023 | Conference paper
Contributors: Khalfaoui-Hassani, Ismail; Pellegrini, Thomas; Masquelier, Timothée
Source: Self-asserted source
Ismail Khalfaoui-Hassani

Adapting a ConvNeXt Model to Audio Classification on AudioSet

INTERSPEECH 2023
2023-08-20 | Conference paper
DOI: 10.21437/interspeech.2023-1564
Contributors: Thomas Pellegrini; Ismail Khalfaoui-Hassani; Etienne Labbé; Timothée Masquelier
Source: Self-asserted source
Ismail Khalfaoui-Hassani via Crossref Metadata Search
grade
Preferred source (of 2)‎

Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing

arXiv preprint arXiv:2210.14151
2022 | Journal article
Contributors: Azadbakht, Alireza; Kheradpisheh, Saeed Reza; Khalfaoui-Hassani, Ismail; Masquelier, Timothée
Source: Self-asserted source
Ismail Khalfaoui-Hassani

The Column Block Cimmino Method - Technical Report

CERFACS, Publications of the Parallel Algorithms Team
2020 | Report
Contributors: Khalfaoui-Hassani, Ismail; Leleux, Philippe; Ruiz, Daniel
Source: Self-asserted source
Ismail Khalfaoui-Hassani
How many people are using ORCID?