| 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 |
|
Kumar, Sandeep
in Cooperation with on an Cooperation-Score of 37%
Topics
Publications (23/23 displayed)
- 2025Multifunctional characterization of high tensile strength PEO/PVP blend based composites with InAs nanowire fillers for structural sodium ion batteries
- 2024Meta-Learning for Real-World Class Incremental Learning: A Transformer-Based Approach
- 2023Influence of single nucleotide polymorphism in the <i>IGF-1</i> gene on performance and conformation traits in Munjal sheepcitations
- 2023Artificial synaptic characteristics of PVA:ZnO nanocomposite memristive devicescitations
- 2023Simultaneous realization of FIR-based multimode optical thermometry and photonic molecular logic gates in Er<sup>3+</sup> and Yb<sup>3+</sup> co-doped SrTiO<sub>3</sub> phosphorcitations
- 2022Feasibility Analysis of Machining Cobalt-Chromium Alloy (Stellite-6) Using TiN Coated Binary Insertscitations
- 2022Mathematical Expressions Model to forecast for Chloride Ion Penetration and Comp. Strength of Recycled Coarse Aggregate Concrete Incorporating Meta-kaolincitations
- 2022Strength Evaluation of Functionalized MWCNT-Reinforced Polymer Nanocomposites Synthesized Using a 3D Mixing Approachcitations
- 2022High performance computing for modelling of stereolithography process
- 2021A nanostructured cellulose-based interphase layer to enhance the mechanical performance of glass fibre-reinforced polymer compositescitations
- 2021Topological phonons in an inhomogeneously strained silicon-2: Evidence of spin-momentum locking
- 2021Topological phonons in an inhomogeneously strained silicon-4: Large spin dependent thermoelectric response and thermal spin transfer torque due to topological electronic magnetism of phonons
- 2020Investigation on the influence of multi-step processing on the mechanical and thermal properties of cellulose reinforced EVOH compositescitations
- 2020High performance multiscale glass fibre epoxy composites integrated with cellulose nanocrystals for advanced structural applicationscitations
- 2020Flexoelectric effect mediated spin-to-charge conversion at amorphous-Si thin film interfaces
- 20201D semiconductor nanowires for energy conversion, harvesting and storage applicationscitations
- 20201D semiconductor nanowires for energy conversion, harvesting and storage applicationscitations
- 2018Recent Advances in Discotic Liquid Crystal-Assisted Nanoparticlescitations
- 2017High electrochemical performance flexible solid-state supercapacitor based on Co-doped reduced graphene oxide and silk fibroin composites.citations
- 2017Carboxybetaine-modified succinylated chitosan-based beads encourage pancreaticβ-cells (Min-6) to form islet-like spheroids under in vitro conditionscitations
- 2017Disturbed Flow Promotes Arterial Stiffening Through Thrombospondin-1citations
- 2015Influence of processing conditions on properties of poly (vinyl acetate)/ cellulose nanocrystals nanocomposites
- 2014Thermal properties and eutectic behaviour of dapivirine in combination with steroid hormones and other antiretrovirals
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>