Views
Graph
Explorer
Focus
Down
Load 1 level
Load 2 levels
Load 3 levels
Load 4 levels
Load all levels
All
Dagre
Focus
Down
Load 1 level
Load 2 levels
Load 3 levels
Load 4 level
Load all levels
All
Tree
SpaceTree
Focus
Expanding
Load 1 level
Load 2 levels
Load 3 levels
Down
All
Down
Radial
Focus
Expanding
Load 1 level
Load 2 levels
Load 3 levels
Down
All
Down
Box
Focus
Expanding
Down
Up
All
Down
Page â
Article
Outline
Document
Down
All
Canvas
Time
Timeline
Calendar
Request email digest
Past 24 hours
Past 2 days
Past 3 days
Past week
Add
Add page
Add comment
Add citation
Edit
Edit page
Delete page
Share
Link
Bookmark
Embed
Social media
Login
Member login
Register now for a free account
đ
David Rumelhart
Protagonist
1
#2772
Arguments advanced by David Rumelhart.
CONTEXT
(Help)
-
Artificial Intelligence »
Artificial Intelligence
Artificial IntelligenceâA collaboratively editable version of Robert Horns brilliant and pioneering debate map Can Computers Think?âexploring 50 years of philosophical argument about the possibility of computer thought.âF1CEB7
▲
Protagonists »
Protagonists
ProtagonistsâThe contributions of over 300 protagonists can be explored via a surname search, or using the growing list developing here.âD3B8AB
■
David Rumelhart
David RumelhartâArguments advanced by David Rumelhart.âD3B8AB
►
Regularity without rules »
Regularity without rules
Regularity without rules âConnectionist networks exhibit lawful behaviour without following explicit rules. Regularities emerge from the interactions of low-level processing units, rather than from the application of high-level rules.âFFFACD
►
The Past-Tense Acquisition Model »
The Past-Tense Acquisition Model
The Past-Tense Acquisition ModelâThis implemented network model was trained to convert English phrases into the past tense. Although the networkâs performance can be described by rules, no actual rules are utilised in its processing.âFFFACD
►
Multilayer perceptrons can compute all relevant functions »
Multilayer perceptrons can compute all relevant functions
Multilayer perceptrons can compute all relevant functionsâThe limitations described by Minsky & Papert dont apply to multilayer networks.âFFFACD
►
Neurons recieve vastly more input »
Neurons recieve vastly more input
Neurons recieve vastly more inputâNeurons are connected to 1,000 to 100,000 other neurons. Logic gates are connected to only a handful of other logic gates. The difference indicates that the brain does not use the king of logical circuitary found in computers.âFFFACD
►
Brain accesses information by content not memory address »
Brain accesses information by content not memory address
Brain accesses information by content not memory addressâHumans rapidly access memories via their contents; eg presidential memories are accessed by information about the presidentâname, face etcânot by an explicit address. Connectionist networks and  brains have content addressable memories of this type.âFFFACD
►
Processing in the brain is distributed »
Processing in the brain is distributed
Processing in the brain is distributedâProcessing in the brain is not mediated by some central control. Neural processing is distributed -- i.e. many regions contribute to the performance of any particular task.âFFFACD
►
Graceful degradation »
Graceful degradation
Graceful degradationâThe brains performance diminishes in proportion to the degree of neuronal damage or noisy input, and gracefully degrades in problematic circumstances. In von Neumann machines, a single glitch tends to have catastrophic consequences for the whole.âFFFACD
►
The brain processes information in parallel »
The brain processes information in parallel
The brain processes information in parallelâVon Neumann machines process information sequentially, one bit at a time. The brain receives and manipulates massive amounts of information at the same time, in parallel.âFFFACD
►
Explicit rules are unnecessary »
Explicit rules are unnecessary
Explicit rules are unnecessaryâConnectionist networks exhibit lawful behaviour without following explicit rules. Reguarlities emerge from the interactions of low-level processing units not from the application of high-level rules.âFFFACD
◄
David Rumelhart »
David Rumelhart
David RumelhartâArguments advanced by David Rumelhart.âFFFACD
Heading
Summary
Click the button to enter task scheduling information
Open
Details
Enter task details
Message text
Select assignee(s)
Due date (click calendar)
RadDatePicker
RadDatePicker
Open the calendar popup.
Calendar
Title and navigation
Title and navigation
<<
<
November 2024
>
<<
November 2024
S
M
T
W
T
F
S
44
27
28
29
30
31
1
2
45
3
4
5
6
7
8
9
46
10
11
12
13
14
15
16
47
17
18
19
20
21
22
23
48
24
25
26
27
28
29
30
49
1
2
3
4
5
6
7
Reminder
No reminder
1 day before due
2 days before due
3 days before due
1 week before due
Ready to post
Copy to text
Enter
Cancel
Task assignment(s) have been emailed and cannot now be altered
Lock
Cancel
Save
Comment graphing options
Choose comments:
Comment only
Whole thread
All comments
Choose location:
To a new map
To this map
New map options
Select map ontology
Options
Standard (default) ontology
College debate ontology
Hypothesis ontology
Influence diagram ontology
Story ontology
Graph to private map
Cancel
Proceed
+Comments (
0
)
- Comments
Add a comment
Newest first
Oldest first
Show threads
+Citations (
0
)
- Citations
Add new citation
List by:
Citerank
Map
+About
- About
Entered by:-
David Price
NodeID:
#2772
Node type:
Protagonist
Entry date (GMT):
7/20/2007 6:05:00 PM
Last edit date (GMT):
7/20/2007 6:05:00 PM
Show other editors
Incoming cross-relations:
1
Outgoing cross-relations:
9
Average rating:
0
by
0
users
x
Select file to upload