Keith A. Pray - Professional and Academic Site
About Me
·
·
·
LinkedIn Profile Facebook Profile GoodReads Profile
Professional
Academic
Teaching
                                          
Printer Friendly Version

Intro ] [ 28-Plan Compilation ] [ 29-ML Survey ] [ 30-Strain Gauge ]

Up: AI in Design ]

Critique: The "What" and "How" of Learning in Design
Duffy *

      So, while many machine learning techniques result from contemplation of human learning characteristics, I think much is lost by viewing only human aspects of learning. Many other forms of life can learn. Does it not make sense to study how other these others learn? Maybe this does not help directly with design but it could provide a foundation more easily applied to computer science than human learning. Duffy certainly takes a human-only approach to describing the "What" and "How" of Learning in Design. While learning is fundamental to people, it is fundamental to many other things. Learning, by definition, changes the state of knowledge and does not depend on where that knowledge resides. If it did, we'd have very little hope of machine learning producing any usable results. Maybe this view is taken since it seems easiest to gain insight into human learning, people being able to communicate, in some capacity, the processes that take place within their own minds.

      When discussing learning from previous designs there is no mention of the kinds of information contained in these previous designs. We've seen great utility in a design case containing the decisions and justifications for those decisions in facilitating the re-use of that previous design to solve new problems. Simply stating that previous designs can be used does not necessarily assume this knowledge is present. Especially in well defined domains, this knowledge helps greatly.

      The over-emphasis of the human aspects of learning appear in a different form in the discussion of induction-based learning and multiple viewpoints. The memory mechanism described is not unique to the human mind but rather, common to most biological memory structures. Since I am not familiar with the referenced work, I cannot say if this occurrence is Duffy's own viewpoint or that of Schank, who Duffy references in this section. It could be that most previous work on which Duffy draws takes this viewpoint of only human-like learning and memory.

      Overall, this article gives a nice overview of the research done up to this point in time. It certainly serves well to peak one's interest in machine learning and specifically, its application to AI design systems. Room could have been made for a slightly more in-depth look at some of this work by trimming down the redundant Machine Learning side bar.


* Alex H.B. Duffy, CAD Centre, University of Strathclyde, The "What" and "How" of Learning in Design, In May/June 1997 IEEE AI in Design

Intro
01-DPMED
02-Dominic
03-DSPL Air-Cyl
04-Pride
05-COSSACK
06-MICOM-M1
07-Configuration Survey
08-Dynamic CSP
09-MOLGEN
10-Failure Handling
11-VT
12-Conflict Resolution
13-Cooperative Negotiation
14-Negotiated Search
15-Multiagent Design
16-Prototypes
17-CBR Survey
18-PROMPT
19-A Design
20-Bogart
21-Cadet
22-Argo
23-Analogy Creativity Survey
24-Algorithm Design
25-AM
26-Edison
27-LEAP
28-Plan Compilation
29-ML Survey
30-Strain Gauge
31-Grammar
32-Config GA
33-Functional First
34-Functional CBR
35-Functional Survey
36-Models
37-First Principles
38-Config Spaces
39-Task Analysis

by: Keith A. Pray
Last Modified: August 13, 2004 8:02 PM
© 2004 - 1975 Keith A. Pray.
All rights reserved.

Current Theme: 

Kapowee Hosted | Kapow Generated in 0.008 second | XHTML | CSS