1 code implementation • 20 May 2024 • Manas Gogoi, Sambhavi Tiwari, Shekhar Verma
However, there can be a number of novel solutions to this problem keeping in mind any of the two objectives to be attained, i. e. to increase diversity in the tasks and to reduce the confidence of the model for some of the tasks.
no code implementations • 2 Sep 2023 • Indrajeet Kumar Sinha, Shekhar Verma, Krishna Pratap Singh
We validate Equitable-FL on the $MNIST$, $F-MNIST$, and $CIFAR-10$ benchmark datasets, as well as the $Brain-MRI$ data and the $PlantVillage$ datasets.
no code implementations • 26 Aug 2023 • Indrajeet Kumar Sinha, Shekhar Verma, Krishna Pratap Singh
There is a need to learn a global model that can be adapted using client's specific information to create personalized models on clients is required.
no code implementations • 18 Aug 2023 • Shikha Verma, Kuldeep Srivastava, Akhilesh Tiwari, Shekhar Verma
Extreme weather events pose significant challenges, thereby demanding techniques for accurate analysis and precise forecasting to mitigate its impact.
no code implementations • 6 Apr 2023 • Sambhavi Tiwari, Manas Gogoi, Shekhar Verma, Krishna Pratap Singh
We aim to perform two things: (a) to find a sub-network capable of more adaptive meta-learning and (b) to learn new low-level features of unseen tasks and recombine those features with the already learned features during the meta-test phase.
no code implementations • 6 Dec 2022 • Lalita Mishra, Shekhar Verma, Shirshu Varma
The method is threefold, in the first step, we normalize and resize the images, and the second step consists of feature extraction through variants of the VGG model.
1 code implementation • 22 Nov 2022 • Manas Gogoi, Sambhavi Tiwari, Shekhar Verma
Prototypical network for Few shot learning tries to learn an embedding function in the encoder that embeds images with similar features close to one another in the embedding space.
no code implementations • 29 Dec 2020 • abhishek, Shekhar Verma
In this paper, the bias due to uneven data sampling on the Riemannian manifold is catered to by a variable Parzen window determined as a function of neighborhood size, ambient dimension, flatness range, etc.