Main.ConnectionismHistory History

Hide minor edits - Show changes to markup

October 17, 2015, at 09:46 PM by 61.238.62.121 -
Changed lines 69-72 from:

Multi-layer networks

to:

Connectionism makes a comeback.

  • Multi-layer networks overcome the limitations of perceptrons
  • More powerful learning algorithms
  • Suggestive psychological applications
October 16, 2015, at 12:37 PM by 202.189.99.39 -
Added lines 33-34:
October 16, 2015, at 08:48 AM by 61.238.62.121 -
Added line 72:
October 16, 2015, at 08:48 AM by 61.238.62.121 -
Changed lines 51-52 from:

Impossible for perceptrons:

to:

Impossible for perceptrons (XOR):

Changed lines 55-58 from:
001
010
100
111
to:
000
011
101
110
October 16, 2015, at 08:45 AM by 61.238.62.121 -
Added lines 66-69:

Multi-layer networks

http://philosophy.hku.hk/joelau/media/rsg1.jpg

October 16, 2015, at 08:45 AM by 61.238.62.121 -
Added lines 35-36:

https://upload.wikimedia.org/wikipedia/en/5/52/Mark_I_perceptron.jpeg

October 16, 2015, at 08:43 AM by 61.238.62.121 -
Added lines 31-32:

Output = f(T)

October 16, 2015, at 08:43 AM by 61.238.62.121 -
Changed lines 28-30 from:

https://upload.wikimedia.org/wikipedia/commons/thumb/3/31/Perceptron.svg/456px-Perceptron.svg.png

The perceptron as a simple one-layer network (wikimedia)

to:

Total input = T = w1x1+ w2x2 + ... + wn xn

October 16, 2015, at 08:41 AM by 61.238.62.121 -
Added lines 37-54:

Easy for perceptrons:

input 1input 2output
000
010
100
111

Impossible for perceptrons:

input 1input 2output
001
010
100
111
October 16, 2015, at 08:20 AM by 61.238.62.121 -
Changed line 30 from:

The perceptron as a simple one-layer network

to:

The perceptron as a simple one-layer network (wikimedia)

October 16, 2015, at 08:20 AM by 61.238.62.121 -
Added lines 27-28:

https://upload.wikimedia.org/wikipedia/commons/thumb/3/31/Perceptron.svg/456px-Perceptron.svg.png

October 16, 2015, at 08:18 AM by 61.238.62.121 -
Changed lines 21-22 from:
  • McCulloch and Pitts (1943). A logical calculus of ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5: 115-133. http://www.mind.ilstu.edu/curriculum/perception/mpneuron1.html
to:
  • McCulloch and Pitts (1943). A logical calculus of ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5: 115-133.
  • Information: http://www.mind.ilstu.edu/curriculum/modOverview.php?modGUI=212
October 16, 2015, at 08:17 AM by 61.238.62.121 -
Changed lines 22-24 from:
  • Hebb, D.O. (1949). The Organization of Behavior. New York: John Wiley Inc.

@Let us assume that the persistence or repetition of a reverberatory activity (or "trace") tends to induce lasting cellular changes that add to its stability.… When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.@

to:

@Let us assume that the persistence or repetition of a reverberatory activity (or "trace") tends to induce lasting cellular changes that add to its stability.… When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.^^^Hebb, D.O. (1949). The Organization of Behavior@

October 16, 2015, at 08:16 AM by 61.238.62.121 -
Changed lines 23-25 from:

@Let us assume that the persistence or repetition of a reverberatory activity (or "trace") tends to induce lasting cellular changes that add to its stability.… When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.@

to:

@Let us assume that the persistence or repetition of a reverberatory activity (or "trace") tends to induce lasting cellular changes that add to its stability.… When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.@

October 16, 2015, at 08:16 AM by 61.238.62.121 -
Changed lines 9-10 from:
  1. Early associationism (up till about 1940)
  2. Beginning connectionism - the age of perceptrons (1943-1969)
to:
  1. Associationism in philosophy (up till about 1940)
  2. The beginning of neural computation and the death of the perceptron (1943-1969)
Changed lines 13-14 from:

Stage 1. Early empiricist associationism in philosophy (up till about 1940)

to:

Stage 1. Early empiricist associationism in philosophy

Changed lines 19-22 from:

Stage 2. The beginning of connectionist computational models - the age of perceptrons (1943-1969)

Theories of the mechanisms of neural computation

to:

Stage 2. The beginning of neural computation

Changed lines 28-31 from:
to:

Hype:

@NEW NAVY DEVICE LEARNS BY DOING; Psychologist Shows Embryo of Computer Designed to Read and Grow Wiser. WASHINGTON, July 7 (UPI) -- The Navy revealed the embryo of an electronic computer today that it expects will be able to walk, talk, see, write, reproduce itself and be conscious of its existence.^^^New York Times@

Changed lines 37-38 from:

Stage 3. The return of connectionism (1970-)

to:
  • Perceptrons cannot solve linearly-nonseparable problems, e.g. XOR

Stage 3. The return of connectionism

October 16, 2015, at 08:05 AM by 61.238.62.121 -
Changed lines 1-2 from:

Readings

to:

Readings

Changed lines 7-10 from:

Stages of connectionism

Three stages:

to:

Three stages in the development of connectionism

Changed lines 13-16 from:

Stage 1. Early associationism (up till about 1940)

Empiricist associationism

to:

Stage 1. Early empiricist associationism in philosophy (up till about 1940)

Changed lines 19-22 from:

Stage 2. Beginning connectionism - the age of perceptrons (1943-1969)

Computational and neural developments

to:

Stage 2. The beginning of connectionist computational models - the age of perceptrons (1943-1969)

Theories of the mechanisms of neural computation

Changed lines 28-32 from:

Setback

to:

The perceptron as a simple one-layer network

Devastating critique and setback

Added line 34:
October 16, 2015, at 08:01 AM by 61.238.62.121 -
Changed lines 17-20 from:

Philosophical background

to:

Empiricist associationism

Changed lines 21-23 from:
  • Empiricist associationism - Hume

@To me, there appear to be only three principles of connexion among ideas, namely, Resemblance, Contiguity in time or place, and Cause or Effect.@

to:

@To me, there appear to be only three principles of connexion among ideas, namely, Resemblance, Contiguity in time or place, and Cause or Effect.^^^David Hume@

October 16, 2015, at 08:00 AM by 61.238.62.121 -
Changed lines 19-21 from:
  • Hobbes (1588-1679)

@For in a discourse of our present civil war, what could seem more impertinent than to ask, as one did, what was the value of a Roman penny? Yet the coherence to me was manifest enough. For the thought of the war introduced the thought of the delivering up the King to his enemies; the thought of that brought in the thought of the delivering up of Christ; and that again the thought of the 30 pence, which was the price of that treason: and thence easily followed that malicious question; and all this in a moment of time, for thought is quick.@

to:

@For in a discourse of our present civil war, what could seem more impertinent than to ask, as one did, what was the value of a Roman penny? Yet the coherence to me was manifest enough. For the thought of the war introduced the thought of the delivering up the King to his enemies; the thought of that brought in the thought of the delivering up of Christ; and that again the thought of the 30 pence, which was the price of that treason: and thence easily followed that malicious question; and all this in a moment of time, for thought is quick.^^^Hobbes (1588-1679)@

January 12, 2009, at 10:36 PM by 219.78.69.186 -
Changed lines 5-6 from:
  • James A. Anderson and Edward Rosenfeld (eds.) Talking Nets hkulib:b1899492
to:
  • James A. Anderson and Edward Rosenfeld (eds.) Talking Nets hkulib:b1899492
January 12, 2009, at 10:36 PM by 219.78.69.186 -
Changed lines 5-6 from:
to:
  • James A. Anderson and Edward Rosenfeld (eds.) Talking Nets hkulib:b1899492
Changed lines 18-21 from:
  • Hobbes
to:
  • Hobbes (1588-1679)

@For in a discourse of our present civil war, what could seem more impertinent than to ask, as one did, what was the value of a Roman penny? Yet the coherence to me was manifest enough. For the thought of the war introduced the thought of the delivering up the King to his enemies; the thought of that brought in the thought of the delivering up of Christ; and that again the thought of the 30 pence, which was the price of that treason: and thence easily followed that malicious question; and all this in a moment of time, for thought is quick.@

Added lines 24-25:

@To me, there appear to be only three principles of connexion among ideas, namely, Resemblance, Contiguity in time or place, and Cause or Effect.@