I agree with you.
~PM

From: [email protected]
To: [email protected]
Subject: RE: [agi] List Similarity
Date: Fri, 21 Feb 2014 08:46:05 +0000







This is an important problem since, in some approaches, patterns will be stored 
as lists.



There are three issues/limitations to your solution below:

- it uses one of the many possible distance metrics

- items in a list may have different weights or relative importance (e.g. 
activation levels) - you assume equal weights in your formula.

- it is really for sets rather than lists.

If one uses a list instead of a set, then there is an explicit ordering element 
(the list index). This order may be very important or just a minor issue. 
Swopping two characters in a word is less important than swopping two notes in 
a tune, which is in turn
 far less of an issue than swopping cause and effect in a chain-reaction list. 
So a good similarity index will be dependent on context. Similar arguments for 
deleting or adding an element.



Jean-Paul Van Belle





From: Piaget Modeler [[email protected]]

Sent: 20 February 2014 20:20

To: AGI

Subject: RE: [agi] List Similarity









(correction) 



The problem is much easier  given two lists



; Premise code (c) 2014 Michael S P Miller






function list-similarity {?A ?B}



  (put (length (intersection ?A ?B)) ?LenAnB)

  (put (length (difference ?A ?B))   ?LenA-B)   

  (put (length (difference ?B ?A))   ?LenB-A)
  (put (length ?A)                   ?LenA)
  (put (length ?B)                   ?LenB)
 
  (return
    (if (or (= ?LenA 0)(= ?LenB 0)) 
       0
     else 
       (* 0.5 (- (+ (/ ?LenAnB ?LenA) (/ ?LenAnB ?LenB))
              (+ (/ ?LenA-B ?LenA) (/ ?LenB-A ?LenB))))))
end 






For numbers, it's a little more difficult.



Your thoughts?









AGI |

Archives 
 | 
Modify Your Subscription











AGI |

Archives 
 | 
Modify Your Subscription









UNIVERSITY OF CAPE TOWN 



This e-mail is subject to the UCT ICT policies and e-mail disclaimer published 
on our website at
http://www.uct.ac.za/about/policies/emaildisclaimer/ or obtainable from +27 21 
650 9111. This e-mail is intended only for the person(s) to whom it is 
addressed. If the e-mail has reached you
 in error, please notify the author. If you are not the intended recipient of 
the e-mail you may not use, disclose, copy, redirect or print the content. If 
this e-mail is not related to the business of UCT it is sent by the sender in 
the sender's individual
 capacity.




  
    
      
      AGI | Archives

 | Modify
 Your Subscription


      
    
  

                                          


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to