Learning Orthographic Structure With Sequential Generative Neural Networks. (14th June 2015)

• Record Type: Journal Article
• Authors: Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco
• Is Part Of: Cognitive science. Volume 40:Number 3(2016:Apr.)
• Page Start: 579
• Page End: 606
• Publication Date: 2015-06-14
• Subjects: Connectionist modeling -- Recurrent neural networks -- Restricted Boltzmann machines -- Probabilistic graphical models -- Generative models -- Unsupervised learning -- Statistical sequence learning -- Orthographic structure; Cognition -- Periodicals; Psycholinguistics -- Periodicals; Artificial intelligence -- Periodicals; 153.05
• DOI: 10.1111/cogs.12258
• Languages: English
• ISSNs: 0364-0213

Abstract

Abstract: Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high‐order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high‐quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non‐connectionist probabilistic models ( n ‐grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain.