Connectionist Approaches to Language Learning

1. Front Matter

   Pages i-iv

   PDF

2. Introduction

   • David S. Touretzky

   Pages 1-3

3. Learning Automata from Ordered Examples

   • Sara Porat, Jerome A. Feldman

   Pages 5-34

4. SLUG: A Connectionist Architecture for Inferring the Structure of Finite-State Environments

   • Michael C. Mozer, Jonathan Bachrach

   Pages 35-56

5. Graded State Machines: The Representation of Temporal Contingencies in Simple Recurrent Networks

   • David Servan-Schreiber, Axel Cleeremans, James L. McClelland

   Pages 57-89

6. Distributed Representations, Simple Recurrent Networks, and Grammatical Structure

   • Jeffrey L. Elman

   Pages 91-121

7. The Induction of Dynamical Recognizers

   • Jordan B. Pollack

   Pages 123-148

8. Back Matter

   Pages 149-149

   PDF

arise automatically as a result of the recursive structure of the task and the continuous nature of the SRN's state space. Elman also introduces a new graphical technique for study­ ing network behavior based on principal components analysis. He shows that sentences with multiple levels of embedding produce state space trajectories with an intriguing self­ similar structure. The development and shape of a recurrent network's state space is the subject of Pollack's paper, the most provocative in this collection. Pollack looks more closely at a connectionist network as a continuous dynamical system. He describes a new type of machine learning phenomenon: induction by phase transition. He then shows that under certain conditions, the state space created by these machines can have a fractal or chaotic structure, with a potentially infinite number of states. This is graphically illustrated using a higher-order recurrent network trained to recognize various regular languages over binary strings. Finally, Pollack suggests that it might be possible to exploit the fractal dynamics of these systems to achieve a generative capacity beyond that of finite-state machines.

• automata
• behavior
• dynamical systems
• learning
• machine learning
• networks

• Carnegie Mellon University, USA

  David Touretzky

Policies and ethics