no code implementations • 4 Jan 2024 • Chi Ian Tang, Lorena Qendro, Dimitris Spathis, Fahim Kawsar, Akhil Mathur, Cecilia Mascolo
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.
1 code implementation • 31 Jul 2023 • Shohreh Deldari, Dimitris Spathis, Mohammad Malekzadeh, Fahim Kawsar, Flora Salim, Akhil Mathur
Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field.
1 code implementation • 30 Mar 2023 • Chi Ian Tang, Lorena Qendro, Dimitris Spathis, Fahim Kawsar, Cecilia Mascolo, Akhil Mathur
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.
1 code implementation • 8 Nov 2022 • Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee, Fahim Kawsar, Akhil Mathur
Federated learning (FL) in multidevice environments creates new opportunities to learn from a vast and diverse amount of private data.
1 code implementation • 23 May 2022 • Ekdeep Singh Lubana, Chi Ian Tang, Fahim Kawsar, Robert P. Dick, Akhil Mathur
Federated learning is generally used in tasks where labels are readily available (e. g., next word prediction).
no code implementations • 17 Feb 2022 • Hyunsung Cho, Akhil Mathur, Fahim Kawsar
Federated Learning (FL) enables distributed training of machine learning models while keeping personal data on user devices private.
no code implementations • 1 Feb 2022 • Yash Jain, Chi Ian Tang, Chulhong Min, Fahim Kawsar, Akhil Mathur
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.
1 code implementation • 19 Jan 2022 • Wiebke Toussaint, Aaron Yi Ding, Fahim Kawsar, Akhil Mathur
Billions of distributed, heterogeneous and resource constrained IoT devices deploy on-device machine learning (ML) for private, fast and offline inference on personal data.
no code implementations • 8 Sep 2021 • Chulhong Min, Akhil Mathur, Utku Gunay Acer, Alessandro Montanari, Fahim Kawsar
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.
no code implementations • 7 Apr 2021 • Akhil Mathur, Daniel J. Beutel, Pedro Porto Buarque de Gusmão, Javier Fernandez-Marques, Taner Topal, Xinchi Qiu, Titouan Parcollet, Yan Gao, Nicholas D. Lane
Federated Learning (FL) allows edge devices to collaboratively learn a shared prediction model while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store data in the cloud.
no code implementations • 15 Feb 2021 • Xinchi Qiu, Titouan Parcollet, Javier Fernandez-Marques, Pedro Porto Buarque de Gusmao, Yan Gao, Daniel J. Beutel, Taner Topal, Akhil Mathur, Nicholas D. Lane
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers.
no code implementations • 1 Jan 2021 • Akhil Mathur, Shaoduo Gan, Anton Isopoussu, Fahim Kawsar, Nadia Berthouze, Nicholas Donald Lane
Breakthroughs in unsupervised domain adaptation (uDA) have opened up the possibility of adapting models from a label-rich source domain to unlabeled target domains.
no code implementations • 4 Dec 2020 • Chulhong Min, Akhil Mathur, Alessandro Montanari, Utku Gunay Acer, Fahim Kawsar
The emergence of multiple sensory devices on or near a human body is uncovering new dynamics of extreme edge computing.
1 code implementation • 3 Nov 2020 • Chongyang Wang, Yuan Gao, Akhil Mathur, Amanda C. De C. Williams, Nicholas D. Lane, Nadia Bianchi-Berthouze
Protective behavior exhibited by people with chronic pain (CP) during physical activities is the key to understanding their physical and emotional states.
no code implementations • 13 Oct 2020 • Xinchi Qiu, Titouan Parcollet, Daniel J. Beutel, Taner Topal, Akhil Mathur, Nicholas D. Lane
Then, we compare the carbon footprint of FL to traditional centralized learning.
1 code implementation • 6 Sep 2020 • Akhil Mathur, Fahim Kawsar, Nadia Berthouze, Nicholas D. Lane
This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models.
1 code implementation • 28 Jul 2020 • Daniel J. Beutel, Taner Topal, Akhil Mathur, Xinchi Qiu, Javier Fernandez-Marques, Yan Gao, Lorenzo Sani, Kwing Hei Li, Titouan Parcollet, Pedro Porto Buarque de Gusmão, Nicholas D. Lane
Federated Learning (FL) has emerged as a promising technique for edge devices to collaboratively learn a shared prediction model, while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store the data in the cloud.
no code implementations • 27 Mar 2020 • Akhil Mathur, Anton Isopoussu, Fahim Kawsar, Nadia Berthouze, Nicholas D. Lane
A major challenge in building systems that combine audio models with commodity microphones is to guarantee their accuracy and robustness in the real-world.
no code implementations • 25 Sep 2019 • Akhil Mathur, Shaoduo Gan, Anton Isopoussu, Fahim Kawsar, Nadia Berthouze, Nicholas D. Lane
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.
1 code implementation • 24 Feb 2019 • Chongyang Wang, Temitayo A. Olugbade, Akhil Mathur, Amanda C. De C. Williams, Nicholas D. Lane, Nadia Bianchi-Berthouze
In chronic pain rehabilitation, physiotherapists adapt physical activity to patients' performance based on their expression of protective behavior, gradually exposing them to feared but harmless and essential everyday activities.