Incremental online learning of objects for robots operating in real environments

Part, Jose L.; Lemon, Oliver

doi:10.1109/devlrn.2017.8329822

Cited by 16 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We list some other references that proposed similar methods based on architectural design [ 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 ], so we will not go into the detail of each.…”

Section: Methods Descriptionmentioning

confidence: 99%

An Appraisal of Incremental Learning Methods

Luo

Yin

Bai

et al. 2020

Entropy

View full text Add to dashboard Cite

As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However, incremental learning remains a long term challenge. Modern deep neural network models achieve outstanding performance on stationary data distributions with batch training. This restriction leads to catastrophic forgetting for incremental learning scenarios since the distribution of incoming data is unknown and has a highly different probability from the old data. Therefore, a model must be both plastic to acquire new knowledge and stable to consolidate existing knowledge. This review aims to draw a systematic review of the state of the art of incremental learning methods. Published reports are selected from Web of Science, IEEEXplore, and DBLP databases up to May 2020. Each paper is reviewed according to the types: architectural strategy, regularization strategy and rehearsal and pseudo-rehearsal strategy. We compare and discuss different methods. Moreover, the development trend and research focus are given. It is concluded that incremental learning is still a hot research area and will be for a long period. More attention should be paid to the exploration of both biological systems and computational models.

show abstract

“…We list some other references that proposed similar methods based on architectural design [ 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 ], so we will not go into the detail of each.…”

Section: Methods Descriptionmentioning

confidence: 99%

An Appraisal of Incremental Learning Methods

Luo

Yin

Bai

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Cortes et al [27] proposed an adaptive learning algorithm called AdaNet, which jointly adapts the network architecture and ensures a trade-off between the empirical risk minimization and model complexity. Xiao et al [28] proposed a learning algorithm which increases hierarchically the capacity of a neural network, while Part et al [29] combined a pre-trained convolution neural network (CNN) and a self-organizing incremental neural network (SOINN). The pre-trained CNN provides good representations from the previously learnt data sets, while the topology of SOINN is evolving continuously according to the input data distribution.…”

Section: Lifelong Learningmentioning

confidence: 99%

Lifelong Teacher-Student Network Learning

Borş

2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

A unique cognitive capability of humans consists in their ability to acquire new knowledge and skills from a sequence of experiences. Meanwhile, artificial intelligence systems are good at learning only the last given task without being able to remember the databases learnt in the past. We propose a novel lifelong learning methodology by employing a Teacher-Student network framework. While the Student module is trained with a new given database, the Teacher module would remind the Student about the information learnt in the past. The Teacher, implemented by a Generative Adversarial Network (GAN), is trained to preserve and replay past knowledge corresponding to the probabilistic representations of previously learn databases. Meanwhile, the Student module is implemented by a Variational Autoencoder (VAE) which infers its latent variable representation from both the output of the Teacher module as well as from the newly available database. Moreover, the Student module is trained to capture both continuous and discrete underlying data representations across different domains. The proposed lifelong learning framework is applied in supervised, semi-supervised and unsupervised training.

show abstract

“…Finally, in model-extension approaches, the model (the network architecture) can be extended itself to accommodate the required capacity for the new task or experience (Draelos et al, 2017). This can be achieved by adding new neurons (Parisi et al, 2017;Part and Lemon, 2017;Doğan et al, 2018a), layers (Rusu et al, 2016;Fernando et al, 2017) or both (Doğan et al, 2018b). Of course, hybrid approaches are also possible.…”

Section: Continual Learningmentioning

confidence: 99%

Mind Your Manners! A Dataset and a Continual Learning Approach for Assessing Social Appropriateness of Robot Actions

2022

View full text Add to dashboard Cite

To date, endowing robots with an ability to assess social appropriateness of their actions has not been possible. This has been mainly due to (i) the lack of relevant and labelled data and (ii) the lack of formulations of this as a lifelong learning problem. In this paper, we address these two issues. We first introduce the Socially Appropriate Domestic Robot Actions dataset (MANNERS-DB), which contains appropriateness labels of robot actions annotated by humans. Secondly, we train and evaluate a baseline Multi Layer Perceptron and a Bayesian Neural Network (BNN) that estimate social appropriateness of actions in MANNERS-DB. Finally, we formulate learning social appropriateness of actions as a continual learning problem using the uncertainty of Bayesian Neural Network parameters. The experimental results show that the social appropriateness of robot actions can be predicted with a satisfactory level of precision. To facilitate reproducibility and further progress in this area, MANNERS-DB, the trained models and the relevant code are made publicly available at https://github.com/jonastjoms/MANNERS-DB.

show abstract

Incremental online learning of objects for robots operating in real environments

Cited by 16 publications

References 17 publications

An Appraisal of Incremental Learning Methods

An Appraisal of Incremental Learning Methods

Lifelong Teacher-Student Network Learning

Mind Your Manners! A Dataset and a Continual Learning Approach for Assessing Social Appropriateness of Robot Actions

Contact Info

Product

Resources

About