Neural Networks and brain Modeling
Last month, a research lab out of Canada unveiled Spaun, the most realistic simulated model of the human brain to date.
The team uses artificial neural networks to simulate sub-regions of the human brain. The sub-regions are then inter-connected in a way that mimics the inter-connectivity of a human brain. The result? Something startlingly human.
I recommend you watch a few videos of Spaun in action.
This project hits particularly close to home. I’ve always believed that artificial neural networks were the key to building truly intelligent artificial systems – after all, why not model artificial intelligence off of our own?
The problem is that there has been a general decline in the popularity of artificial neural networks in the academic community over the last few decades. Two of the most salient arguments against artificial neural networks have been, respectively, 1) that they must be pre-trained and can’t rapidly adapt without damaging old training and 2) that the underlying structure of the network is invisible, especially when complex (or dynamic) topologies are used.
Spaun illustrates that with a self-regulating model and multiple inter-connected networks, adaptive behavior can be achieved with artificial neural networks. Spaun also shows us that by discretizing neural network topologies in to analogies of organic brain components, we can develop more manageable models.
You might also like:
Short answer2001-06-13 12:10:13 by datamouse
An article in Rolling Stone (October 20, 1994) by Adam Miller called J. Philippe Rushton a 'professor of hate,' someone who 'takes money from an organization with a terrible past' (the Pioneer Fund, a foundation said to have an orientation toward eugenics). He is accused of being 'obsessed with intelligence and genetics' to the point of having 'racist' attitudes by Jeffrey Rosen and Charles Lane in The New Republic symposium on IQ (October 31, 1994). They single out Rushton for linking ethnocentricism to genetic factors; this in turn subjects him to the broad brush of being, along with Richard J. Herrnstein and Charles Murray, 'Neo-Nazis' Newsweek (October 24, 1994). In The Chronicle of Higher Education (October 26, 1994) critiquing Herrnstein and Murray's The Bell Curve it is clear...
MOOCs: A review — The MIT Tech
Machine Learning (ML), taught by Coursera co-founder Andrew Ng SM '98, is a broad overview of popular machine learning algorithms such as linear and logistic regression, neural networks, SVMs, and k-means clustering, among others. It is light on theory ...