If you just have a single problem to solve, then fine, go ahead and use a neural network. But if you want to do science and understand how to choose architectures, or how to go to a new problem, you have to understand what different architectures can and cannot do.
Interpretation
Understanding neural networks requires knowledge of their capabilities and limitations beyond just solving individual problems.
Marvin Minsky's quote emphasizes the importance of comprehending the underlying principles of neural network architectures rather than using them as mere tools for specific problems. A deeper understanding allows scientists and practitioners to choose the right approaches for various challenges in the field of artificial intelligence, fostering innovation and the ability to tackle new problems effectively.
In practice
During a lecture on artificial intelligence, this quote can illustrate the importance of foundational knowledge in the field.
If you understand something in only one way, then you don't really understand it at all. The secret of what anything means to us depends on how we've connected it to all other things we know. Well-connected representations let you turn ideas around in your mind, to envision things from many perspectives until you find one that works for you. And that's what we mean by thinking!
There was a failure to recognize the deep problems in AI; for instance, those captured in Blocks World. The people building physical robots learned nothing.
You don't understand anything unless you understand there are at least 3 ways.
I think every person either inherits or eventually makes up their own idea of what they are and who they are and what caused the world to be, and it seems to me that these stories of creation myth, adopted by different cultures - most of them are less insightful than the stories made up by individual poets and writers.
I believe that everyone has to construct a mental model of what they are and where they came from and why they are as they are, and the word soul in each person is the name for that particular mish-mash of those fully formed ideas of one's nature.
You don't understand anything until you learn it more than one way.
There are all kinds of interesting questions that come from a knowledge of science, which only adds to the excitement and mystery and awe of a flower.
I would say the biggest handicap we have right now is some nutcases in our country that don't believe in global warming. I think they are going to change their position because of pressure from individuals, because the evidence of the ravages of global warming is already there.
Certainly I see the scientific view of the world as incompatible with religion, but that is not what is interesting about it. It is also incompatible with magic, but that also is not worth stressing. What is interesting about the scientific world view is that it is true, inspiring, remarkable and that it unites a whole lot of phenomena under a single heading.
'Goals' and 'caps' on carbon emissions are practically worthless, if coal emissions continue, because of the exceedingly long lifetime of carbon dioxide in the air.
To set foot on the soil of the asteroids, to lift by hand a rock from the Moon, to observe Mars from a distance of several tens of kilometers, to land on its satellite or even on its surface, what can be more fantastic? From the moment of using rocket devices a new great era will begin in astronomy: the epoch of the more intensive study of the firmament.
Any work of science, no matter what its point of departure, cannot become fully convincing until it crosses the boundary between the theoretical and the experimental: Experimentation must give way to argument, and argument must have recourse to experimentation.
Subscribe for the occasional hand-picked quote. No noise.