NEXT STORY
My early methods for testing neural networks
RELATED STORIES
Video URL
How I became interested in neural networks
Marvin Minsky
Scientist
|
Views | Duration | |
|---|---|---|---|
| 21. A short history of neural networks | 1494 | 02:30 | |
| 22. How I became interested in neural networks | 1 | 1245 | 01:53 |
| 23. My early methods for testing neural networks | 1053 | 02:10 | |
| 24. My PhD thesis on learning machines | 1190 | 01:06 | |
| 25. John Nash solves my PhD problem | 1857 | 01:48 | |
| 26. Why I changed from bottom-up to top-down thinking | 2 | 2561 | 02:39 |
| 27. The end of my PhD on learning machines | 1188 | 04:24 | |
| 28. My first encounter with a computer | 1 | 1014 | 01:56 |
| 29. Writing a program for Russell Kirsch's SEAC | 896 | 01:54 | |
| 30. The first timeshared computer | 864 | 01:03 |
-
- 1
- 2
- 3
- 4
- 5
- ...
- 16
-
Comments
(0)
Please sign in or
register to add comments
I got interested in neural network ideas from reading a few papers in that great book by Nicholas Rashevsky, a book called Mathematical Biophysics, and... I’m trying to remember the year, there was… among other things he had a journal which published this first paper by McCulloch and Pitts about neural networks. Well, it was maybe the second paper on the logic of neural networks, because Sigmund Freud had actually written one in 1894 or '95, in the from of a paper called Project For A Scientific Psychology, and I believe that paper was turned down for publication, so Freud never got it published, and it wasn’t actually published till 1950. So that’s an interesting story which we should look up... get the dates right. But anyway, I started to work on trying to make... take the McCulloch-Pitts theory of how neural networks could simulate any machine, a very general theory, and I was interested in making more particular specialised theory of how to make neural networks that could learn.
Marvin Minsky (1927-2016) was one of the pioneers of the field of Artificial Intelligence, founding the MIT AI lab in 1970. He also made many contributions to the fields of mathematics, cognitive psychology, robotics, optics and computational linguistics. Since the 1950s, he had been attempting to define and explain human cognition, the ideas of which can be found in his two books, The Emotion Machine and The Society of Mind. His many inventions include the first confocal scanning microscope, the first neural network simulator (SNARC) and the first LOGO 'turtle'.
Title: How I became interested in neural networks
Listeners: Christopher Sykes
Christopher Sykes is a London-based television producer and director who has made a number of documentary films for BBC TV, Channel 4 and PBS.
Tags: Mathematical Biophysics, Project for a Scientific Psychology, 1950, Nicolas Rashevsky, Warren McCulloch, Walter Pitts, Sigmund Freud
Duration: 1 minute, 54 seconds
Date story recorded: 29-31 Jan 2011
Date story went live: 09 May 2011
