research
∙
09/12/2023
The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models
Large Language Models (LLMs) have demonstrated remarkable generalization...
share
research
∙
07/31/2023
Latent Masking for Multimodal Self-supervised Learning in Health Timeseries
Limited availability of labeled data for machine learning on biomedical ...
research
∙
07/22/2023
The State of Algorithmic Fairness in Mobile Human-Computer Interaction
This paper explores the intersection of Artificial Intelligence and Mach...
research
∙
03/30/2023
Practical self-supervised continual learning with continual fine-tuning
Self-supervised learning (SSL) has shown remarkable performance in compu...
research
∙
03/27/2023
Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing
The field of mobile, wearable, and ubiquitous computing (UbiComp) is und...
research
∙
11/08/2022
Centaur: Federated Learning for Constrained Edge Devices
Federated learning (FL) on deep neural networks facilitates new applicat...
research
∙
05/23/2022
Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
Federated learning is generally used in tasks where labels are readily a...
research
∙
02/17/2022
FLAME: Federated Learning Across Multi-device Environments
Federated Learning (FL) enables distributed training of machine learning...
research
∙
02/01/2022
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
A major bottleneck in training robust Human-Activity Recognition models ...
research
∙
01/19/2022
Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows
Billions of distributed, heterogeneous and resource constrained smart co...
research
∙
12/26/2021
FRuDA: Framework for Distributed Adversarial Domain Adaptation
Breakthroughs in unsupervised domain adaptation (uDA) can help in adapti...
research
∙
09/08/2021
SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices
We present SensiX++ - a multi-tenant runtime for adaptive model executio...
research
∙
01/27/2021
Low-Power Audio Keyword Spotting using Tsetlin Machines
The emergence of Artificial Intelligence (AI) driven Keyword Spotting (K...
research
∙
12/04/2020
SensiX: A Platform for Collaborative Machine Learning on the Edge
The emergence of multiple sensory devices on or near a human body is unc...
research
∙
09/06/2020
Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
This paper introduces a new dataset, Libri-Adapt, to support unsupervise...
research
∙
03/27/2020
Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systems
Mobile and embedded devices are increasingly using microphones and audio...
research
∙
10/10/2018