|Name:||Dr James V Stone|
|Email:||j.v.stone at sheffield.ac.uk|
|Department:||Psychology Department, Sheffield University|
Publications (most can be downloaded).
Publications listed by Google Scholar.
My principal interests are:
1) generic computational principles which underpin visual perception (eg spatiotemporal smoothness, statistical independence, information maximisation, Bayesian inference),
2) the relationship between learning and evolution.
MatLab code for reinforcement learning can be downloaded fromhere. This code implements the Markov chain example given on page 18 of RS Sutton's paper "Learning to predict by the methods of temporal differences" Machine Learning, 3, pp9-44, 1988.
MatLab code for the Baldwin effect, as described in Hinton and Nowlan's
paper, can be obtained here.
G. E. Hinton and S. J. Nowlan. How learning can guide evolution. Complex Systems, 1:495--502, 1987.
Surely, God could have caused birds to fly with their bones made of solid gold, with their veins full of quicksilver, with their flesh heavier than lead, and with their wings exceedingly small. He did not, and that ought to show something. It is only in order to shield your ignorance that you put the Lord at every turn to the refuge of a miracle.
Galileo Galilei (1564 -1642)