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. Marvin Minsky aheadarchitecturechoose share on social
Around 1967 Dan Bobrow wrote a program to do algebra problems based on symbols rather than numbers. Marvin Minsky algebrabasebobrow Change image and share on social
In general we are least aware of what our minds do best. Marvin Minsky awaregeneralmind Change image and share on social
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. Marvin Minsky blockbuildcapture Change image and share on social
We wanted to solve robot problems and needed some vision, action, reasoning, planning, and so forth. We even used some structural learning, such as was being explored by Patrick Winston. Marvin Minsky actionexplorelearn Change image and share on social
There are three basic approaches to AI: Case-based, rule-based, and connectionist reasoning. Marvin Minsky approachbasebasic Change image and share on social
When David Marr at MIT moved into computer vision, he generated a lot of excitement, but he hit up against the problem of knowledge representation; he had no good representations for knowledge in his vision systems. Marvin Minsky computerdavidexcitement share on social
No computer has ever been designed that is ever aware of what it's doing; but most of the time, we aren't either. Marvin Minsky awarecomputerdesign Change image and share on social
I believed in realism, as summarized by John McCarthy's comment to the effect that if we worked really hard, we'd have an intelligent system in from four to four hundred years. Marvin Minsky believecommenteffect Change image and share on social
