<html>
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
On 4/18/08 3:38 PM, Asim Roy wrote:<br>
> By the way, your algorithms I believe are structurally similar
to the other connectionists algorithms I analyzed in my paper.<br>
<br>
Asim, I respectfully disagree. <br>
If what you said is true, it is absolutely impossible for me to
bridge the wide gap between the two major schools in AI:<br>
the symbolic school and the connectionist school. <br>
Please see the (incomplete) 14-point list of novelties below from an
anonymous reviewer. I first introduce the wide gap:<br>
<br>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
Marvin Minsky 1991 in AI Magazine:<br>
- Symbolic: Logic & Neat<br>
- Connectionist: analogical & scruffy.<br>
Michael Jordan at IJCNN 2011:<br>
- Neural nets do not abstract well<br>
- I will not talk about neural nets today<br>