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, 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. We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. (shrink)

Sibley, Kello, Plaut, and Elman (2008) proposed the sequence encoder as a model that learns fixed‐width distributed representations of variable‐length sequences. In doing so, the sequence encoder overcomes problems that have restricted models of word reading and recognition to processing only monosyllabic words. Bowers and Davis (2009) recently claimed that the sequence encoder does not actually overcome the relevant problems, and hence it is not a useful component of large‐scale word‐reading models. In this reply, it is noted that the sequence (...) encoder has facilitated the creation of large‐scale word‐reading models. The reasons for this success are explained and stand as counterarguments to claims made by Bowers and Davis. (shrink)

The forms of words as they appear in text and speech are central to theories and models of lexical processing. Nonetheless, current methods for simulating their learning and representation fail to approach the scale and heterogeneity of real wordform lexicons. A connectionist architecture termed thesequence encoderis used to learn nearly 75,000 wordform representations through exposure to strings of stress‐marked phonemes or letters. First, the mechanisms and efficacy of the sequence encoder are demonstrated and shown to overcome problems with traditional slot‐based (...) codes. Then, two large‐scale simulations are reported that learned to represent lexicons of either phonological or orthographic wordforms. In doing so, the models learned the statistics of their lexicons as shown by better processing of well‐formed pseudowords as opposed to ill‐formed (scrambled) pseudowords, and by accounting for variance in well‐formedness ratings. It is discussed how the sequence encoder may be integrated into broader models of lexical processing. (shrink)

This paper introduces a special issue of Cognitive Science initiated on the 25th anniversary of the publication of Parallel Distributed Processing (PDP), a two-volume work that introduced the use of neural network models as vehicles for understanding cognition. The collection surveys the core commitments of the PDP framework, the key issues the framework has addressed, and the debates the framework has spawned, and presents viewpoints on the current status of these issues. The articles focus on both historical roots and contemporary (...) developments in learning, optimality theory, perception, memory, language, conceptual knowledge, cognitive control, and consciousness. Here we consider the approach more generally, reviewing the original motivations, the resulting framework, and the central tenets of the underlying theory. We then evaluate the impact of PDP both on the field at large and within specific subdomains of cognitive science and consider the current role of PDP models within the broader landscape of contemporary theoretical frameworks in cognitive science. Looking to the future, we consider the implications for cognitive science of the recent success of machine learning systems called “deep networks”—systems that build on key ideas presented in the PDP volumes. (shrink)

I consider the role of cognitive modeling in cognitive science. Modeling, and the computers that enable it, are central to the field, but the role of modeling is often misunderstood. Models are not intended to capture fully the processes they attempt to elucidate. Rather, they are explorations of ideas about the nature of cognitive processes. In these explorations, simplification is essential—through simplification, the implications of the central ideas become more transparent. This is not to say that simplification has no downsides; (...) it does, and these are discussed. I then consider several contemporary frameworks for cognitive modeling, stressing the idea that each framework is useful in its own particular ways. Increases in computer power (by a factor of about 4 million) since 1958 have enabled new modeling paradigms to emerge, but these also depend on new ways of thinking. Will new paradigms emerge again with the next 1,000‐fold increase? (shrink)

It has been recently argued that some machine learning techniques known as Kernel methods could be relevant for capturing cognitive and neural mechanisms (Jäkel, Schölkopf, & Wichmann, 2009). We point out that ‘‘String kernels,’’ initially designed for protein function prediction and spam detection, are virtually identical to one contending proposal for how the brain encodes orthographic information during reading. We suggest some reasons for this connection and we derive new ideas for visual word recognition that are successfully put to the (...) test. We argue that the versatility and performance of String kernels makes a compelling case for their implementation in the brain. (shrink)

Sibley et al. (2008) report a recurrent neural network model designed to learn wordform representations suitable for written and spoken word identification. The authors claim that their sequence encoder network overcomes a key limitation associated with models that code letters by position (e.g., CAT might be coded as C‐in‐position‐1, A‐in‐position‐2, T‐in‐position‐3). The problem with coding letters by position (slot‐coding) is that it is difficult to generalize knowledge across positions; for example, the overlap between CAT and TOMCAT is lost. Although we (...) agree this is a critical problem with many slot‐coding schemes, we question whether the sequence encoder model addresses this limitation, and we highlight another deficiency of the model. We conclude that alternative theories are more promising. (shrink)