Related papers: Efficient Hardware Implementation of Incremental L…
Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses…
Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…
As quantum computers continue to improve and support larger, more complex computations, smart control hardware and compilers are needed to efficiently leverage the capabilities of these systems. This paper introduces a novel approach to…
Although CNNs have gained the ability to transfer learned knowledge from source task to target task by virtue of large annotated datasets but consume huge processing time to fine-tune without GPU. In this paper, we propose a new…
LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from…
Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data…
Nowadays a diverse range of physiological data can be captured continuously for various applications in particular wellbeing and healthcare. Such data require efficient methods for classification and analysis. Deep learning algorithms have…
The exponential growth of Internet-connected devices has presented challenges to traditional centralized computing systems due to latency and bandwidth limitations. Edge computing has evolved to address these difficulties by bringing…
Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…
Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is…
In order to track and comprehend the academic achievement of students, both private and public educational institutions devote a significant amount of resources and labour. One of the difficult issues that institutes deal with on a regular…
Incremental learning that learns new classes over time after the model's deployment is becoming increasingly crucial, particularly for industrial edge systems, where it is difficult to communicate with a remote server to conduct…
Spikes are the currency in central nervous systems for information transmission and processing. They are also believed to play an essential role in low-power consumption of the biological systems, whose efficiency attracts increasing…
Deep neural networks (DNNs) have the advantage that they can take into account a large number of parameters, which enables them to solve complex tasks. In computer vision and speech recognition, they have a better accuracy than common…
Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies…
Keyword spotting has gained popularity as a natural way to interact with consumer devices in recent years. However, because of its always-on nature and the variety of speech, it necessitates a low-power design as well as user customization.…
As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…
The advancements in machine learning opened a new opportunity to bring intelligence to the low-end Internet-of-Things nodes such as microcontrollers. Conventional machine learning deployment has high memory and compute footprint hindering…