Related papers: An Ultra-Low Power Wearable BMI System with Contin…

Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The…

Artificial intelligence systems in critical fields like autonomous driving and medical imaging analysis often continually learn new tasks using a shared stream of input data. For instance, after learning to detect traffic signs, a model may…

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

Lengthy subject- or session-specific data acquisition and calibration remain a key barrier to deploying electroencephalography (EEG)-based brain-computer interfaces (BCIs) outside the laboratory. Previous work has shown that cross subject,…

Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual…

Humans and animals learn throughout their lives from limited amounts of sensed data, both with and without supervision. Autonomous, intelligent robots of the future are often expected to do the same. The existing continual learning (CL)…

Since cadiovascular disease (CVD) posts a heavy threat to people's health, long-term electrocardiogram (ECG) monitoring is of great value for the improvement of treatment. To realize remote long-term ECG monitoring, a low-power wireless…

Automatic gym activity recognition on energy- and resource-constrained wearable devices removes the human-interaction requirement during intense gym sessions - like soft-touch tapping and swiping. This work presents a tiny and highly…

Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have…

The rapid growth of microcontroller-based IoT devices has opened up numerous applications, from smart manufacturing to personalized healthcare. Despite the widespread adoption of energy-efficient microcontroller units (MCUs) in the Tiny…

To adapt to real-world data streams, continual learning (CL) systems must rapidly learn new concepts while preserving and utilizing prior knowledge. When it comes to adding new information to continually-trained deep neural networks (DNNs),…

Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards…

Emerging non-volatile memory (NVM), or memristive, devices promise energy-efficient realization of deep learning, when efficiently integrated with mixed-signal integrated circuits on a CMOS substrate. Even though several algorithmic…

This study offers a revolutionary strategy to developing wheelchairs based on the Brain-Computer Interface (BCI) that incorporates Artificial Intelligence (AI) using a The device uses electroencephalogram (EEG) data to mimic wheelchair…

Continual Learning (CL) is crucial for enabling networks to dynamically adapt as they learn new tasks sequentially, accommodating new data and classes without catastrophic forgetting. Diverging from conventional perspectives on CL, our…

Continual learning (CL) aims to learn new tasks while retaining past knowledge, addressing the challenge of forgetting during task adaptation. Rehearsal-based methods, which replay previous samples, effectively mitigate forgetting. However,…

This paper introduces a new, highly energy-efficient, Adiabatic Capacitive Neuron (ACN) hardware implementation of an Artificial Neuron (AN) with improved functionality, accuracy, robustness and scalability over previous work. The paper…

Many machine learning frameworks have been proposed and used in wireless communications for realizing diverse goals. However, their incapability of adapting to the dynamic wireless environment and tasks and of self-learning limit their…

The "pre-training $\rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through Parameter-Efficient-Tuning (PET) adaptation…

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…