English
Related papers

Related papers: An Online Learning Algorithm for Neuromorphic Hard…

200 papers

This paper presents a novel projection-based adaptive algorithm for sparse signal and system identification. The sequentially observed data are used to generate an equivalent sequence of closed convex sets, namely hyperslabs. Each hyperslab…

Information Theory · Computer Science 2015-10-28 Yannis Kopsinis , Konstantinos Slavakis , Sergios Theodoridis

Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Traditional backpropagation, while effective, conflicts with…

Machine Learning · Computer Science 2025-10-31 Darius Masoum Zadeh-Jousdani , Elvin Hajizada , Eyke Hüllermeier

This paper presents a neurosymbolic framework to solve motion planning problems for mobile robots involving temporal goals. The temporal goals are described using temporal logic formulas such as Linear Temporal Logic (LTL) to capture…

Robotics · Computer Science 2022-10-12 Xiaowu Sun , Yasser Shoukry

Multi-agent reinforcement learning (MARL) is a powerful technology to construct interactive artificial intelligent systems in various applications such as multi-robot control and self-driving cars. Unlike supervised model or single-agent…

Hardware Architecture · Computer Science 2022-11-01 Je Yang , JaeUk Kim , Joo-Young Kim

With the emergence of diverse and massive data in the upcoming sixth-generation (6G) networks, the task-agnostic semantic communication system is regarded to provide robust intelligent services. In this paper, we propose a task-agnostic…

Information Theory · Computer Science 2025-09-16 Shiyao Jiang , Jian Jiao , Xingjian Zhang , Ye Wang , Dusit Niyato , Qinyu Zhang

This paper studies graph-based active learning, where the goal is to reconstruct a binary signal defined on the nodes of a weighted graph, by sampling it on a small subset of the nodes. A new sampling algorithm is proposed, which…

Machine Learning · Computer Science 2016-05-19 Eyal En Gad , Akshay Gadde , A. Salman Avestimehr , Antonio Ortega

The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as…

Computer Vision and Pattern Recognition · Computer Science 2019-05-10 Donggeun Yoo , In So Kweon

Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of computational power, robust learning and energy efficiency. We…

Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test…

Machine Learning · Computer Science 2022-01-25 Tianyang Wang , Xingjian Li , Pengkun Yang , Guosheng Hu , Xiangrui Zeng , Siyu Huang , Cheng-Zhong Xu , Min Xu

Symbolic regression is a technique that can automatically derive analytic models from data. Traditionally, symbolic regression has been implemented primarily through genetic programming that evolves populations of candidate solutions…

Neural and Evolutionary Computing · Computer Science 2025-04-24 Jiří Kubalík , Robert Babuška

It is hard to directly implement Graph Neural Networks (GNNs) on large scaled graphs. Besides of existed neighbor sampling techniques, scalable methods decoupling graph convolutions and other learnable transformations into preprocessing and…

Machine Learning · Computer Science 2021-07-02 Chuxiong Sun , Hongming Gu , Jie Hu

This study addresses the challenge of online learning in contexts where agents accumulate disparate data, face resource constraints, and use different local algorithms. This paper introduces the Switched Online Learning Algorithm (SOLA),…

Machine Learning · Computer Science 2023-12-12 Darshan Gadginmath , Shivanshu Tripathi , Fabio Pasqualetti

Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution shifts. In practice, annotators make mistakes, rare…

Machine Learning · Computer Science 2025-10-14 Atharv Goel , Sharat Agarwal , Saket Anand , Chetan Arora

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…

Computer Vision and Pattern Recognition · Computer Science 2017-06-16 Mehran Khodabandeh , Zhiwei Deng , Mostafa S. Ibrahim , Shinichi Satoh , Greg Mori

Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research,…

Machine Learning · Computer Science 2018-06-14 Kunkun Pang , Mingzhi Dong , Yang Wu , Timothy Hospedales

Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Yibing Fu , Yunpeng Zhao , Zhitao Zeng , Cheng Chen , Yueming Jin

We propose an interpretable framework for reading analog gauges that is deployable on real world robotic systems. Our framework splits the reading task into distinct steps, such that we can detect potential failures at each step. Our system…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Maurits Reitsma , Julian Keller , Kenneth Blomqvist , Roland Siegwart

Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data, which is not applicable in practical re-id deployment. In this work, we propose a Support Pair Active Learning (SPAL) framework to…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 Dapeng Jin , Minxian Li

The goal of neural-symbolic computation is to integrate the connectionist and symbolist paradigms. Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the…

Machine Learning · Statistics 2020-07-29 Qing Li , Siyuan Huang , Yining Hong , Yixin Chen , Ying Nian Wu , Song-Chun Zhu

Imitation learning is a popular method for teaching robots new behaviors. However, most existing methods focus on teaching short, isolated skills rather than long, multi-step tasks. To bridge this gap, imitation learning algorithms must not…

Artificial Intelligence · Computer Science 2025-11-04 Leon Keller , Daniel Tanneberg , Jan Peters