Exploring system performance of continual learning for mobile and embedded sensing applications
Continual learning approaches help deep neural network models adapt and learn
incrementally by trying to solve catastrophic forgetting. However, whether these existing …
incrementally by trying to solve catastrophic forgetting. However, whether these existing …
Yono: Modeling multiple heterogeneous neural networks on microcontrollers
Internet of Things (IoT) systems provide large amounts of data on all aspects of human
behavior. Machine learning techniques, especially deep neural networks (DNN), have …
behavior. Machine learning techniques, especially deep neural networks (DNN), have …
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
Continual Learning (CL) allows applications such as user personalization and household
robots to learn on the fly and adapt to context. This is an important feature when context …
robots to learn on the fly and adapt to context. This is an important feature when context …
Class-incremental learning for time series: Benchmark and evaluation
Z Qiao, Q Pham, Z Cao, HH Le, PN Suganthan… - arXiv preprint arXiv …, 2024 - arxiv.org
Real-world environments are inherently non-stationary, frequently introducing new classes
over time. This is especially common in time series classification, such as the emergence of …
over time. This is especially common in time series classification, such as the emergence of …
Enabling on-device smartphone GPU based training: Lessons learned
Deep Learning (DL) has shown impressive performance in many mobile applications. Most
existing works have focused on reducing the computational and resource overheads of …
existing works have focused on reducing the computational and resource overheads of …
Improving feature generalizability with multitask learning in class incremental learning
Many deep learning applications, like keyword spotting [1],[2], require the incorporation of
new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The …
new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The …
Task incremental learning with static memory for audio classification without catastrophic interference
The deep neural network shows excellent performance on a single task. However, deep
neural networks performance degraded when trained continuously on a sequence of new …
neural networks performance degraded when trained continuously on a sequence of new …
Myokey: Inertial motion sensing and gesture-based qwerty keyboard for extended realities
Usability challenges and social acceptance of textual input in a context of extended realities
(XR) motivate the research of novel input modalities. We investigate the fusion of inertial …
(XR) motivate the research of novel input modalities. We investigate the fusion of inertial …
Characterizing Continual Learning Scenarios and Strategies for Audio Analysis
Audio analysis is useful in many application scenarios. The state-of-the-art audio analysis
approaches assume that the data distribution at training and deployment time will be the …
approaches assume that the data distribution at training and deployment time will be the …
A Min-Heap-Based Accelerator for Deterministic On-the-Fly Pruning in Neural Networks
Z Jelčicová, E Kasapaki, O Andersson… - … Symposium on Circuits …, 2023 - ieeexplore.ieee.org
This paper addresses the design of an area and energy efficient hardware accelerator that
supports on-the-fly pruning in neural networks. In a layer of N neurons, the accelerator …
supports on-the-fly pruning in neural networks. In a layer of N neurons, the accelerator …