Search Results for author:
Found 22 papers, 7 papers with code
Time-bound Contextual Bio-ID Generation for Minimalist Wearables
As wearable devices become increasingly miniaturized and powerful, a new opportunity arises for instant and dynamic device-to-device collaboration and human-to-device interaction.
Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras
Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis.
Balancing Continual Learning and Fine-tuning for Human Activity Recognition
These schemes re-purpose contrastive learning for knowledge retention and, Kaizen combines that with self-training in a unified scheme that can leverage unlabelled and labelled data for continual learning.
Evaluating Fairness in Self-supervised and Supervised Models for Sequential Data
Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels.
Collaborative Inference via Dynamic Composition of Tiny AI Accelerators on MCUs
The advent of tiny AI accelerators opens opportunities for deep neural network deployment at the extreme edge, offering reduced latency, lower power cost, and improved privacy in on-device ML inference.
Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing
In split inference, a deep neural network (DNN) is partitioned to run the early part of the DNN at the edge and the later part of the DNN in the cloud.
The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models
Here, we discuss recent works that employ LLMs for human-centric tasks such as in mobile health sensing and present a case study showing that popular LLMs tokenize temporal data incorrectly.
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field.
Towards personalised music-therapy; a neurocomputational modelling perspective
In particular, the direct interaction of auditory with the motor and the reward system via a predictive framework explains the efficacy of music-based interventions in motor rehabilitation.
Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning
Kaizen is able to balance the trade-off between knowledge retention and learning from new data with an end-to-end model, paving the way for practical deployment of continual learning systems.
Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing
The field of mobile and wearable computing is undergoing a revolutionary integration of machine learning.
Enhancing Efficiency in Multidevice Federated Learning through Data Selection
Federated learning (FL) in multidevice environments creates new opportunities to learn from a vast and diverse amount of private data.
Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
Federated learning is generally used in tasks where labels are readily available (e. g., next word prediction).
FLAME: Federated Learning Across Multi-device Environments
Federated Learning (FL) enables distributed training of machine learning models while keeping personal data on user devices private.
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
In this paper, we extend this line of research and present a novel technique called Collaborative Self-Supervised Learning (ColloSSL) which leverages unlabeled data collected from multiple devices worn by a user to learn high-quality features of the data.
Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows
Billions of distributed, heterogeneous and resource constrained IoT devices deploy on-device machine learning (ML) for private, fast and offline inference on personal data.
SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices
We present SensiX++ - a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e. g., a camera, a microphone, or IoT sensors.
Scaling Unsupervised Domain Adaptation through Optimal Collaborator Selection and Lazy Discriminator Synchronization
Breakthroughs in unsupervised domain adaptation (uDA) have opened up the possibility of adapting models from a label-rich source domain to unlabeled target domains.
SensiX: A Platform for Collaborative Machine Learning on the Edge
The emergence of multiple sensory devices on or near a human body is uncovering new dynamics of extreme edge computing.
Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models.
Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systems
A major challenge in building systems that combine audio models with commodity microphones is to guarantee their accuracy and robustness in the real-world.
Multi-Step Decentralized Domain Adaptation
Despite the recent breakthroughs in unsupervised domain adaptation (uDA), no prior work has studied the challenges of applying these methods in practical machine learning scenarios.
