Example networks for Mesh

Example networks for the Mesh neural network simulator:

• net_input: Simple activation propagation example;

• boolean_functions: These examples are taken from chapter 3 of Plunkett and Elman (1997);

• reading_aloud: This example implements the Reading Aloud network of Plaut et al. (1996), as discussed in chapter 8 of McLeod et al. (1998);

• english_past_tense: This example implements the English Past Tense network of Plunkett and Marchman (1991), as discussed in chapter 9 of McLeod et al. (1998);

• consonant_vowels: This example is taken from chapter 8 of Plunkett and Elman (1997);

• next_word_prediction: A simple next word prediction model trained on the sentences of Venhuizen et al. (2019);

• expectation_comprehension: This implements the comprehension model of Venhuizen et al. (2019);

• language_production: Exercise: Turn the comprehension model of Venhuizen et al. (2019) into a model of production.

References

McLeod, P., Plunkett, K. and Rolls, E. T. (1998). Introduction to Connectionist Modelling of Cognitive Processes. Oxford University Press.

Plaut, D.C., McClelland, J.L., Seidenberg, M.S., and Patterson, K. (1996). Understanding normal and impaired word reading: Computational principles in quasi-regular domains. Psychological Review, 103, 56-115.

Plunkett, K., and Elman, J. (1997). Exercises in rethinking innateness: A Handbook for Connectionist Simulations. MIT Press.

Plunkett, K., and Marchman, V. (1991). U-shaped learning and frequency effects in a multi-layered perceptron: Implications for child language acquisition. Cognition, 38, 43-102.

Venhuizen, N. J., Crocker, M. W., and Brouwer, H. (2019). Expectation-based Comprehension: Modeling the Interaction of World Knowledge and Linguistic Experience. Discourse Processes, 56:3, 229-255.