SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model

Abstract

To realize human-like robot intelligence, a large-scale cognitive architecture is required for robots to understand their environment through a variety of sensors with which they are equipped. In this paper, we propose a novel framework named Serket that enables the construction of a large-scale generative model and its inferences easily by connecting sub-modules to allow the robots to acquire various capabilities through interaction with their environment and others. We consider that large-scale cognitive models can be constructed by connecting smaller fundamental models hierarchically while maintaining their programmatic independence. Moreover, the connected modules are dependent on each other and their parameters must be optimized as a whole. Conventionally, the equations for parameter estimation have to be derived and implemented depending on the models. However, it has become harder to derive and implement equations of large-scale models. Thus, in this paper, we propose a parameter estimation method that communicates the minimum parameters between various modules while maintaining their programmatic independence. Therefore, Serket makes it easy to construct large-scale models and estimate their parameters via the connection of modules. Experimental results demonstrated that the model can be constructed by connecting modules, the parameters can be optimized as a whole, and they are comparable with the original models that we have proposed.

Neuro-SERKET: Development of Integrative Cognitive System Through the Composition of Deep Probabilistic Generative Models

“…Numerous types of integrative cognitive systems, which are sometimes called a cognitive architecture, have recently been developed for building service robots and modeling human adaptive cognition [2][3][4][5][6][7][8][9][10][11]. However, the cognitive systems for robots need to handle a variety of types of sensorimotor modalities, e.g., image, sound and actuation, and a variety of internal cognitive processes, e.g., categorization and planning.…”

“…This paper describes a novel framework enabling researchers and developers to create elemental cognitive modules, i.e., image recognition, automatic speech recognition, and syntax and clustering models, independently, and compose them into a large cognitive system, which can operate as a cognitive system and be consistently trained as a single learning system. Neuro-SERKET is an extension of SER-KET [11], which was proposed as a framework for decomposing and composing PGMs. As described later, SERKET does not support neural networks, i.e., deep learning.…”

“…Fig. 1 A robot planning and conducting a multimodal object categorization using a complex PGM [7] SERKET is a framework proposed for solving this problem [11]. SERKET was designed to enable a distributed software development of extremely large PGMs.…”

Improved and scalable online learning of spatial concepts and language models with mapping

“…We will explore whether the SpCoSLAM model proposed herein can be integrated with other probabilistic models to form a large-scale cognitive model for generalpurpose autonomous intelligent robots using a SERKET architecture (Nakamura et al 2018). However, applications of the SERKET architecture are limited due to its computational cost for learning the enormous parameters of the whole model.…”

Symbol Emergence in Cognitive Developmental Systems: A Survey

“…Developing an architecture that is decomposable and comprehensible while providing consistent learning results is important. Nakamura et al introduced a framework called SERKET, which enable us to develop cognitive components independently and allows them to work and learn together in the same theoretical way, as they are developed as a single learning system [134]. Computational models and frameworks to develop a largescale cognitive architecture that can work practically in the real-world environment is our challenge.…”