Bag of multimodal hierarchical dirichlet processes: Model of complex conceptual structure for intelligent robots

Nagaoka, Tomoaki; Nagai, Takayuki; Iwahashi, Naoto

doi:10.1109/iros.2012.6385502

Cited by 12 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, to form the concept of "yellow," a color sense is important, whereas haptic and auditory information are not necessary. A combination of MLDA and MHDP methods has been proposed and demonstrated to be capable of searching for appropriate correspondences between categories and modalities (Nakamura et al, 2011a(Nakamura et al, , 2012. Nakamura et al (2015) also proposed a non-parametric Bayesian extension of these models.…”

Section: Multi-modal Concept Formation and Representation Learningmentioning

confidence: 99%

Collective Predictive Coding Hypothesis: Symbol Emergence as Decentralized Bayesian Inference

Taniguchi¹

2023

Preprint

View full text Add to dashboard Cite

Understanding the emergence of symbol systems, especially language, requires constructing a computational model that reproduces both the developmental learning process in everyday life and the evolutionary dynamics of symbol emergence throughout history. This paper introduces the collective predictive coding (CPC) hypothesis. The CPC emphasizes and models the interdependence between forming internal representations through physical interactions with the environment and sharing and utilizing meanings via social semiotic interactions within a symbol emergence system, and theorizes the total dynamics from the viewpoint of {\it predictive coding}. This hypothesis draws inspiration from computational studies grounded in probabilistic generative models and the Metropolis-Hastings naming game, which is a type of language game. It suggests that playing this type of game among agents in a distributed manner can be interpreted as a decentralized Bayesian inference of representations shared among a multi-agent system. Moreover, this paper explores the potential link between the CPC hypothesis and the free-energy principle, positing that symbol emergence adheres to a society-wide free-energy principle. The paper reviews past approaches to symbol emergence systems. The paper also offers a comprehensive survey of the related prior studies and discusses how the CPC might generalize these perspectives. It also highlights future challenges and potential cross-disciplinary research avenues.

show abstract

Section: Multi-modal Concept Formation and Representation Learningmentioning

confidence: 99%

Collective Predictive Coding Hypothesis: Symbol Emergence as Decentralized Bayesian Inference

Taniguchi¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Nakamura et al proposed the Bag of MLDA (BoMLDA), Bag of the MHDP (BoMHDP), and infinite mixture of MHDPs (IMoMHDPs) methods, which can perform various types of categorization with different perspectives [46,56,64]. The methods emphasize some modalities, and organize categories based on information of the modalities focused on.…”

Section: Estimating Latent Structure In Multimodal Categoriesmentioning

confidence: 99%

Symbol Emergence in Robotics: A Survey

Taniguchi

Nagai

Nagaoka

et al. 2015

Preprint

Self Cite

View full text Add to dashboard Cite

Humans can learn the use of language through physical interaction with their environment and semiotic communication with other people. It is very important to obtain a computational understanding of how humans can form a symbol system and obtain semiotic skills through their autonomous mental development. Recently, many studies have been conducted on the construction of robotic systems and machine-learning methods that can learn the use of language through embodied multimodal interaction with their environment and other systems. Understanding human social interactions and developing a robot that can smoothly communicate with human users in the long term, requires an understanding of the dynamics of symbol systems and is crucially important. The embodied cognition and social interaction of participants gradually change a symbol system in a constructive manner. In this paper, we introduce a field of research called symbol emergence in robotics (SER). SER is a constructive approach towards an emergent symbol system. The emergent symbol system is socially selforganized through both semiotic communications and physical interactions with autonomous cognitive developmental agents, i.e., humans and developmental robots. Specifically, we describe some state-ofart research topics concerning SER, e.g., multimodal categorization, word discovery, and a double articulation analysis, that enable a robot to obtain words and their embodied meanings from raw sensory-motor information, including visual information, haptic information, auditory information, and acoustic speech signals, in a totally unsupervised manner. Finally, we suggest future directions of research in SER.

show abstract

On Parallelism in Music and Language: A Perspective from Symbol Emergence Systems Based on Probabilistic Generative Models

Taniguchi

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Bag of multimodal hierarchical dirichlet processes: Model of complex conceptual structure for intelligent robots

Cited by 12 publications

References 15 publications

Collective Predictive Coding Hypothesis: Symbol Emergence as Decentralized Bayesian Inference

Collective Predictive Coding Hypothesis: Symbol Emergence as Decentralized Bayesian Inference

Symbol Emergence in Robotics: A Survey

On Parallelism in Music and Language: A Perspective from Symbol Emergence Systems Based on Probabilistic Generative Models

Contact Info

Product

Resources

About