Deep ART Neural Model for Biologically Inspired Episodic Memory and Its Application to Task Performance of Robots

Park, Gyeong-Moon; Yoo, Yong-Ho; Kim, Deok-Hwa; Kim, Jong-Hwan

doi:10.1109/tcyb.2017.2715338

Cited by 25 publications

(16 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep ART network was developed to learn temporal information for biologically inspired episodic memory [16]. This network has one more layer than the Fusion ART network, as depicted in Fig.…”

Section: B Deep Art Networkmentioning

confidence: 99%

“…By the work of many researchers, the ART network has been improved so that it can handle complicated input patterns [9]- [11]. Recently, the ART network was utilized for classification and recommendation [12], [13], hybrid data regression [14], topological clustering [15], implementation of long term memory [16]- [19], and interactive learning [20]. However, ART networks still have limitations in direct application to AI tutors.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose an AI tutor that provides individualized education programs to learners considering their current status and preferences. To this end, we develop an integrated system of three developmental learning networks (DLNs): learner status DLN, learner preference DLN, and learner experience DLN based on the Deep ART network [16]. Specifically, we propose a new algorithm for each DLN; individual algorithms respectively deal with the limitations as mentioned above.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Individualized AI Tutor Based on Developmental Learning Networks

Kim

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In recent years, in the field of education technology, artificial intelligence tutors have come to be expected to provide individualized educational services to help learners achieve high levels of academic success. To this end, AI tutors need to be able to understand the current status and preferences of a learner and then suggest appropriate learning contents accordingly. However, it is challenging to monitor learner status and preferences continually and to recommend appropriate educational services. In this paper, we propose an individualized AI tutor as an integrated system of three developmental learning networks (DLNs) by extending a deep adaptive resonance theory (Deep ART) network, a neural network capable of incremental learning. Specifically, the learner status DLN is able to easily add new input channels about learner status without disrupting existing classifiers. The learner preference DLN is to categorize learner preferences based on frequency as well as sequence of events. The learner experience DLN is updated to immediately reflect alteration of the educational effectiveness in the current classification. Our AI tutor is currently embedded in a commercialized mobile application for teaching the Korean language to children. Experimental results show that the AI tutor application efficiently helps children learn the Korean language.

show abstract

Section: B Deep Art Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Individualized AI Tutor Based on Developmental Learning Networks

Kim

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…A different approach is to persist instances of the working memory that were involved in solving a specific problem and subsequently retrieve previous solutions from the episodic memory. Thereby, planning can be enhanced and even facilitate one-shot learning capabilities [5]- [9]. Predominantly, instances stored in the episodic memory are symbolic highlevel representations [7], [10].…”

Section: A Episodic Memory and Cognitive Architecturesmentioning

confidence: 99%

Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution

Rothfuss

Ferreira

Aksoy

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences. Our proposed unsupervised deep episodic memory model 1) encodes observed actions in a latent vector space and, based on this latent encoding, 2) infers most similar episodes previously experienced, 3) reconstructs original episodes, and 4) predicts future frames in an end-to-end fashion. Results show that conceptually similar actions are mapped into the same region of the latent vector space. Based on these results, we introduce an action matching and retrieval mechanism, benchmark its performance on two large-scale action datasets, 20BN-something-something and ActivityNet and evaluate its generalization capability in a real-world scenario on a humanoid robot.

show abstract

“…In this paper, we 1) design a stabilized memory system with a feedback mechanism for incremental learning and 2) propose an integrated robot-IoT framework for home service provision. For the design of a memory system, we base our design on an adaptive resonance theory (ART) network [30]- [32]. With the capability of adaptive pattern recognition and robust handling of temporal-spatial relations, the ART network can fully take the role of intelligence required to learn and infer a personalized service.…”

mentioning

confidence: 99%

A Stabilized Feedback Episodic Memory (SF-EM) and Home Service Provision Framework for Robot and IoT Collaboration

Kim

2020

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

The automated home referred to as Smart Home is expected to offer fully customized services to its residents, reducing the amount of home labor, thus improving human beings' welfare. Service robots and Internet of Things (IoT) play the key roles in the development of Smart Home. The service provision with these two main components in a Smart Home environment requires: 1) learning and reasoning algorithms and 2) the integration of robot and IoT systems. Conventional computational intelligence-based learning and reasoning algorithms do not successfully manage dynamic changes in the Smart Home data, and the simple integrations fail to fully draw the synergies from the collaboration of the two systems. To tackle these limitations, we propose: 1) a stabilized memory network with a feedback mechanism which can learn user behaviors in an incremental manner and 2) a robot-IoT service provision framework for a Smart Home which utilizes the proposed memory architecture as a learning and reasoning module and exploits synergies between the robot and IoT systems. We conduct a set of comprehensive experiments under various conditions to verify the performance of the proposed memory architecture and the service provision framework and analyze the experiment results.Index Terms-Ambient intelligence, Internet of Things (IoT), learning systems, memory architecture, service robots, Smart Home.

show abstract

Deep ART Neural Model for Biologically Inspired Episodic Memory and Its Application to Task Performance of Robots

Cited by 25 publications

References 33 publications

Individualized AI Tutor Based on Developmental Learning Networks

Individualized AI Tutor Based on Developmental Learning Networks

Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution

A Stabilized Feedback Episodic Memory (SF-EM) and Home Service Provision Framework for Robot and IoT Collaboration

Contact Info

Product

Resources

About