Mindful Active Learning

Ashari, Zhila Esna; Ghasemzadeh, Hassan

doi:10.24963/ijcai.2019/314

“…Zhao et al [192] actively select samples that are relabeled multiple times through crowd-sourcing majority voting. EMMA [193] relabels samples to remove noisy annotations by analyzing the stimulus based on model memory retention and greedy heuristics. BALT [203] improves human expertise during labeling to improve relabel quality and significantly improve model performance.…”

Section: Challenges and Opportunities Of Dalmentioning

confidence: 99%

A Survey on Deep Active Learning: Recent Advances and New Frontiers

Li,

Wang,

Chen

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

1

0

View full text Add to dashboard Cite

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label newly selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep active learning (DAL), remain scarce. Therefore, we conduct an advanced and comprehensive survey on DAL. We first introduce reviewed paper collection and filtering. Second, we formally define the DAL task and summarize the most influential baselines and widely used datasets. Third, we systematically provide a taxonomy of DAL methods from five perspectives, including annotation types, query strategies, deep model architectures, learning paradigms, and training processes, and objectively analyze their strengths and weaknesses. Then, we comprehensively summarize the main applications of DAL in natural language processing (NLP), computer vision (CV), data mining (DM), and so on. Finally, we discuss challenges and perspectives after a detailed analysis of current studies. This work aims to serve as a useful and quick guide for researchers in overcoming difficulties in DAL. We hope that this survey will spur further progress in this burgeoning field.

show abstract

“…A wide variety of approaches and applications have been proposed for enhancing robotic agents with active learning techniques (Kulick et al 2013;Cakmak and Thomaz 2012;Cakmak, Chao, and Thomaz 2010;Chao, Cakmak, and Thomaz 2010;Ribes et al 2015;Hayes and Scassellati 2014;Huang, Jin, and Zhou 2010;Ashari and Ghasemzadeh 2019). In these works, the robotic agents improve their skills or learn new concepts by collecting and labeling data in an online way.…”

Section: Related Workmentioning

confidence: 99%

Planning for Learning Object Properties

Lamanna¹,

Serafini²,

Faridghasemnia³

et al. 2023

Preprint

1

0

View full text Add to dashboard Cite

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.

show abstract

“…A wide variety of approaches and applications have been proposed for enhancing robotic agents with active learning techniques (Kulick et al 2013;Cakmak and Thomaz 2012;Cakmak, Chao, and Thomaz 2010;Chao, Cakmak, and Thomaz 2010;Ribes et al 2015;Hayes and Scassellati 2014;Huang, Jin, and Zhou 2010;Ashari and Ghasemzadeh 2019). In these works, the robotic agents improve their skills or learn new concepts by collecting and labeling data in an online way.…”

Section: Related Workmentioning

confidence: 99%

Planning for Learning Object Properties

Lamanna

¹

,

Serafini

²

,

Faridghasemnia

³

et al. 2023

AAAI

1

0

View full text Add to dashboard Cite

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.

show abstract

Mindful Active Learning

Abstract: Contact Author 1 Software for EMMA (Entropy-Memory Maximization) is available at https://github.com/zhesna/EMMA.

Cited by 9 publications

References 5 publications

A Survey on Deep Active Learning: Recent Advances and New Frontiers

A Survey on Deep Active Learning: Recent Advances and New Frontiers

Planning for Learning Object Properties

Planning for Learning Object Properties

Contact Info

Product

Resources

About