Customer Reviews

Rethinking Innateness: A Connectionist Perspective on Development (Neural Network Modeling and Connectionism)

5 star:		(2)
4 star:		(0)
3 star:		(1)
2 star:		(0)
1 star:		(0)

 

 

I came across this book while studying applied linguistics, and was curious about what Connectionist theory had to say against Noam Chomsky's nativist approach, which is that language is too complex a thing to be learned in the same way that we learn to swim or drive a car, and that it must be genetically ingrained, with a specific "language gene" that determines the fundamental parameters of how all human languages work.

Until reading this, I had heard all the conventional arguments against connectionsim -it was all computers and had nothing to do with the human mind, no computer simulation could ever come close to mimicing the complexity of the human mind, etc.

This book, mostly concerned with human development, has some fascinating and paradigm-changing ideas to add to the debate. If genes are so important, the authors argue, why don't we come out of the womb as fully formed adults with everything we need to know hardwired into us, as some lower species are? The authors show that there are simple flowers that have more genes than we do, demonstrating that gene count isn't the last word on an organism's complexity.

The authors make a powerful case that the state of childhood , and the complex development our minds experience during this time, is the reason that genes with specific codings don't have to do all the work- we are formed in interaction with our environments.

Rather than explaining everything, connectionist models simply demonstrate how, on the simplest level, our minds COULD work. While the models are simple, the results are fascinating. While obviously far less complex, the models really do demonstrate some of the quirks of human learning and acquisition in ways that more rigid, rule-based artificial intelligence doesn't.

I could write more, but this is a sprawling book packed with countless ideas, and even a brief summary would cover several pages. I admit that it can get technical at times, and I had to limit my reading of it to a few pages a day to fully digest it. But if you want to learn about this subject and have the dedication to get through it, it's an extremely worthwhile and rewarding investment of your time.

This book contains some thoughtful reasons for believing that many evolutionary psychologists overestimate how much information about the human mind is encoded in genes. However, it is mixed in with some highly technical developmental neurobiology that only a few specialists are likely to find interesting.
For nonspecialists, David Buller's book Adapting Minds says similar things about innateness in a style that is more suited for laymen.

Grammar isn't encoded in our genomes. It is learned. The beginnings of the proof are here. This is an important book. Read it and it's companion: Exercises in Rethinking Innateness : A Handbook for Connectionist Simulations; which gives you hands on with the models discussed.