| People | Locations | Statistics |
|---|---|---|
| Naji, M. |
| |
| Motta, Antonella |
| |
| Aletan, Dirar |
| |
| Mohamed, Tarek |
| |
| Ertürk, Emre |
| |
| Taccardi, Nicola |
| |
| Kononenko, Denys |
| |
| Petrov, R. H. | Madrid |
|
| Alshaaer, Mazen | Brussels |
|
| Bih, L. |
| |
| Casati, R. |
| |
| Muller, Hermance |
| |
| Kočí, Jan | Prague |
|
| Šuljagić, Marija |
| |
| Kalteremidou, Kalliopi-Artemi | Brussels |
|
| Azam, Siraj |
| |
| Ospanova, Alyiya |
| |
| Blanpain, Bart |
| |
| Ali, M. A. |
| |
| Popa, V. |
| |
| Rančić, M. |
| |
| Ollier, Nadège |
| |
| Azevedo, Nuno Monteiro |
| |
| Landes, Michael |
| |
| Rignanese, Gian-Marco |
|
Sharma, Amit
in Cooperation with on an Cooperation-Score of 37%
Topics
Publications (26/26 displayed)
- 2024Pulsed electrodeposition of homogenous and heterogeneous solid solution layered structure in high strength nanocrystalline Co–Cu alloyscitations
- 2024Micromechanics reveal strain rate dependent transition between dislocation mechanisms in a dual phase high entropy alloy ; La micromécanique révèle une transition entre les mécanismes de dislocation dépendant de la vitesse de déformation dans un alliage à double phase et à haute entropie
- 2024Meta-Learning for Real-World Class Incremental Learning: A Transformer-Based Approach
- 2024Magnetron sputter deposition of amorphous silicon–SiO 2 quantized nanolaminatescitations
- 2024Magnetron Sputter Deposition of Amorphous Silicon–SiO<sub>2</sub> Quantized Nanolaminatescitations
- 2024Micromechanical response of an electrodeposited NiP metallic glass by pillar compression under extreme conditionscitations
- 2023Synthesis and mechanical properties of co-deposited W nanoparticle and ZrCuAg metallic glass thin film compositescitations
- 2023Mechanical properties and thermal stability of thin film metallic glass compared to bulk metallic glass from ambient to elevated temperaturescitations
- 2023Fabrication and extreme micromechanics of additive metal microarchitecturescitations
- 2023Unlocking the potential of CuAgZr metallic classes: a comprehensive exploration with combinatorial synthesis, high-throughput characterization, and machine learningcitations
- 2023Solid-solution and precipitation softening effects in defect-free faceted nickel-iron nanoparticlescitations
- 2023Strengthening of 3D printed Cu micropillar in Cu-Ni core-shell structurecitations
- 2023Combinatorial reactive sputtering with Auger parameter analysis enables synthesis of wurtzite Zn 2 TaN 3citations
- 2023Cutting-edge advances in modeling the blood-brain barrier and tools for its reversible permeabilization for enhanced drug delivery into the braincitations
- 2023Correlated disorder by defects clusters in LiNbO3 single crystals after crys-tal ion-slicingcitations
- 2023Machine learning of twin/matrix interfaces from local stress field
- 2022Microstructure evolution and mechanical response of a boron-modified Ti-6Al-4V alloy during high-pressure torsion processingcitations
- 2022IoT Based Smart Sewerage Management System for Moradabad City
- 2022Hybrid hierarchical nanolattices with porous platinum coatingcitations
- 2022Corrosion behavior of a series of combinatorial physical vapor deposition coatings on SiC in a simulated boiling water reactor environmentcitations
- 2021Direct observation of the elasticity-texture relationship in pyrolytic carbon via in situ micropillar compression and digital image correlationcitations
- 2021Thermal stability of thin Au films deposited on salt whiskerscitations
- 2021When more is less: plastic weakening of single crystalline Ag nanoparticles by the polycrystalline Au shellcitations
- 2020Recent Nanocarrier Approaches for Targeted Drug Delivery in Cancer Therapycitations
- 2019Grain growth and solid-state dewetting of Bi-Crystal Ni-Fe thin films on sapphirecitations
- 2017Titanium aluminium nitride and titanium boride multilayer coatings designed to combat tool wearcitations
Places of action
| Organizations | Location | People |
|---|
document
Meta-Learning for Real-World Class Incremental Learning: A Transformer-Based Approach
Abstract
<jats:title>Abstract</jats:title><jats:p>Modern Natural Language Processing (NLP) state-of-the-art (SoTA) Deep Learning (DL) models have hundreds of millions of parameters, making them extremely complex. Large datasets are required for training these models, and while pretraining has reduced this requirement, human-labelled datasets are still necessary for fine-tuning. Few-Shot Learning (FSL) techniques, such as meta-learning, try to train models from smaller datasets to mitigate this cost. However, the tasks used to evaluate these meta-learners frequently diverge from the problems in the real world that they are meant to resolve. This work aims to apply meta-learning to a problem that is more pertinent to the real world: class incremental learning (IL). In this scenario, after completing its training, the model learns to classify newly introduced classes. One unique quality of meta-learners is that they can generalise from a small sample size to classes that have never been seen before, which makes them especially useful for class incremental learning (IL). The method describes how to emulate class IL using proxy new classes. This method allows a meta-learner to complete the task without the need for retraining. To generate predictions, the transformer-based aggregation function in a meta-learner that modifies data from examples across all classes has been proposed. The principal contributions of the model include concurrently considering the entire support and query sets, and prioritising attention to crucial samples, such as the question, to increase the significance of its impact during inference. The outcomes demonstrate that the model surpasses prevailing benchmarks in the industry. Notably, most meta-learners demonstrate significant generalisation in the context of class IL even without specific training for this task. This paper establishes a high-performing baseline for subsequent transformer-based aggregation techniques, thereby emphasising the practical significance of meta-learners in class IL.</jats:p>