Neuro-SERKET: Development of Integrative Cognitive System Through the Composition of Deep Probabilistic Generative Models
Neuro-SERKET: Development of Integrative Cognitive System Through the Composition of Deep Probabilistic Generative Models
复制标题
DOI：
10.1007/s00354-019-00084-w
复制
发表时间：
2020-01-22
影响因子：
2.6
通讯作者：
Nagai, Takayuki
中科院分区：
文献类型：
--
作者：
Taniguchi, Tadahiro;Nakamura, Tomoaki;Nagai, Takayuki
本文描述了一个框架的发展的基础上概率生成模型（PGMs）称为Neuro-SERKET的综合认知系统。Neuro-SERKET是SERKET的扩展，它可以组成以分布式方式开发的基本PGM，并提供一种允许组成的PGM以无监督的方式在整个系统中学习的方案。除了SERKET支持的头到尾连接之外，Neuro-SERKET还支持尾到尾和头到头连接，以及基于神经网络的模块，即，深层生成模型作为神经SERKET应用的一个例子，通过组成变分自动编码器（VAE），高斯混合模型（GMM），潜在的狄利克雷分配（LDA），和自动语音识别（ASR）的综合模型。该模型称为VAE + GMM + LDA + ASR。VAE + GMM + LDA + ASR的性能和Neuro-SERKET的有效性通过多模态分类任务使用图像数据和数字的语音信号被证明。
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.