no code implementations • 8 Mar 2024 • Enoch Solomon, Abraham Woubie
Federated learning facilitates the training of a shared model without necessitating the sharing of individual private data, achieving this by training models on decentralized edge devices housing the data.
no code implementations • 22 Dec 2023 • Enoch Solomon, Abraham Woubie, Eyael Solomon Emiru
In this work, we propose a method to narrow this gap by leveraging an autoencoder to convert the face image vector into a novel representation.
no code implementations • 21 Dec 2023 • Abraham Woubie, Enoch Solomon, Eyael Solomon Emiru
In this work, we propose the use of RBMs to the image clustering tasks.
no code implementations • 21 Dec 2023 • Enoch Solomon, Abraham Woubie, Eyael Solomon Emiru
Achieving state-of-the-art results in face verification systems typically hinges on the availability of labeled face training data, a resource that often proves challenging to acquire in substantial quantities.
no code implementations • 21 Dec 2023 • Enoch Solomon, Abraham Woubie, Eyael Solomon Emiru
Initially, an autoencoder is trained in an unsupervised manner using a substantial amount of unlabeled training dataset.
no code implementations • 13 Jun 2020 • Abrhalei Tela, Abraham Woubie, Ville Hautamaki
Thus, using XLNet language model, we demonstrate competitive performance with mBERT and a pre-trained target language model on the cross-lingual sentiment (CLS) dataset and on a new sentiment analysis dataset for low-resourced language Tigrinya.
no code implementations • 10 May 2019 • Abraham Woubie, Anssi Kanervisto, Janne Karttunen, Ville Hautamaki
In this work, we propose the use of audio as complementary information to visual only in state representation.