This paper describes a framework for the development of an integrative cognitive system based on probabilistic generative models (PGMs) called Neuro-SERKET. Neuro-SERKET is an extension of SERKET, which can compose elemental PGMs developed in a distributed manner and provide a scheme that allows the composed PGMs to learn throughout the system in an unsupervised way. In addition to the head-to-tail connection supported by SERKET, Neuro-SERKET supports tail-to-tail and head-to-head connections, as well as neural network-based modules, i.e., deep generative models. As an example of a Neuro-SERKET application, an integrative model was developed by composing a variational autoencoder (VAE), a Gaussian mixture model (GMM), latent Dirichlet allocation (LDA), and automatic speech recognition (ASR). The model is called VAE + GMM + LDA + ASR. The performance of VAE + GMM + LDA + ASR and the validity of Neuro-SERKET were demonstrated through a multimodal categorization task using image data and a speech signal of numerical digits.

中文翻译：

---

Neuro-SERKET：通过深度概率生成模型的组合开发综合认知系统

本文描述了一个基于概率生成模型 (PGM) 的集成认知系统的开发框架，称为 Neuro-SERKET。Neuro-SERKET 是 SERKET 的扩展，它可以组合以分布式方式开发的元素 PGM，并提供一种方案，允许组合的 PGM 以无监督的方式在整个系统中学习。除了SERKET支持的head-to-tail连接，Neuro-SERKET还支持tail-to-tail和head-to-head连接，以及基于神经网络的模块，即深度生成模型。作为 Neuro-SERKET 应用程序的一个示例，通过组合变分自动编码器 (VAE)、高斯混合模型 (GMM)、潜在狄利克雷分配 (LDA) 和自动语音识别 (ASR) 来开发集成模型。该模型称为VAE+GMM+LDA+ASR。