Learning by Ignoring the Most Wrong
Abstract Imprecise probabilities (IP) are an increasingly popular way of reasoning about rational credence. However they are subject to an apparent failure to display convincing inductive learning. This paper demonstrates that a small modification to the update rule for IP allows us to overcome this problem, albeit at the cost of satisfying only a weaker concept of coherence.
1990 ◽
Vol 48
(1)
◽
pp. 202-203
1994 ◽
Vol 58
(11)
◽
pp. 832-835
◽
1998 ◽
Vol 138
(2)
◽
pp. 205-205
Keyword(s):
2006 ◽
Vol 2006
◽
pp. 148
2014 ◽
Vol 84
(5-6)
◽
pp. 244-251
◽