Category
2,117 papers
Edge translation systems must balance limited computation, data locality, and weak performance on low-resource language pairs. This study presents Multitask Bayesian Federated Learning (MT-BayesFL), a multilingual translation framework that combines a lightweight shared encoder, task-specific decoders, matrix-normal po...
Federated learning (FL) presents a promising paradigm for training machine learning models on decentralized data, preserving data privacy. However, this approach is increasingly recognized to be vulnerable to algorithmic bias. The inherent diversity and potential imbalances within the data contributed by numerous clien...
A novel federated transfer learning framework for accurate classification of renal abnormalities using 12,446 kidney CT scan images and simultaneously preserves data privacy is proposed, highlighting its potential for deployment in distributed clinical environments for kidney disease diagnosis.
João Carlos Amaro Ferreira (ISCTE-IUL, 16/07/2021), showcasing the research group's work in IoT, edge/fog computing, and data science. The group has expertise in edge/fog architectures (open-source and commercial platforms), IoT communications (short and long range, lightweight protocols such as MQTT/CoAP, V2X), and di...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Federated learning (FL) lets distributed intrusion-detection systems (IDS) train on private traffic, but exposes the global model to poisoning and backdoor attacks under non-IID client data. A popular defense family scores or filters clients using a small trusted "root" dataset and the similarity of client behaviour to...
Blockchain-Anchored Provenance for Federated Learning under Variable IoT Device Availability
Modern computing environments integrate Linux servers, Windows workstations, and Android devices, creating fragmented security telemetry that limits the detection of coordinated cross-platform attacks. This paper proposes DSSN-V4, a unified distributed framework for cross-platform threat monitoring and global risk asse...
Modern computing environments integrate Linux servers, Windows workstations, and Android devices, creating fragmented security telemetry that limits the detection of coordinated cross-platform attacks. This paper proposes DSSN-V4, a unified distributed framework for cross-platform threat monitoring and global risk asse...
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data without directly exchanging the data itself. However, FL systems are vulnerable to Byzantine attacks, where malicious participants introduce corrupted data or models to compromise the learning process. This pap...
The Wisdom Continuum: A Unified Theory of Human Development, Learning, Intelligence, Artificial Intelligence, and Civilizational Evolution Description / Abstract The Wisdom Continuum presents a civilizational-scale framework that unifies human development, moral philosophy, educational reform, and artificial intelligen...
L-shaped SFT is presented, a split fine-tuning framework that removes the need for continuous client participation and introduces one-shot SFT, in which clients upload activations once and then go offline while the server continues optimization over cached representations.
This paper presents a novel approach to distributed learning leveraging Federated Bayesian Networks (FBNs). Traditional federated learning methods struggle with capturing complex, non-independent data distributions, often leading to suboptimal global models. We introduce a framework where multiple devices collaborative...
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
Education Innovation
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
A Blog post by NVIDIA on Hugging Face
A Blog post by IBM Research on Hugging Face
A new machine-learning approach broke records for weather forecasting for an important time frame in emergency planning.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
