top of page
.png){kind=small}
"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."
Standard
Customized
Exlpore more Science quotes
"At the end of all spiritual paths, there lies only a cold graveyard; the path of science is the only path that may give you something better than this!"
"There are stars in the night sky that look brighter than the others, and when you look at them through a telescope you realize you are looking at twins. The two stars rotate around each other, sometimes taking nearly a hundred years to do it. They create so much gravitational pull there's no room around for anything else. You might see a blue star, for example, and realize only later that it has a white dwarf as a companion - that first one shines so bright, by the time you notice the second one, it's too late."
"No definite sciencewithout trial & error."
"Science is knowledge meeting humility meeting curiosity: ever-evolving, always learning. Atheism is often but knowledge meeting arrogance: a masquerade under the wing of the beauty of science. Religion is infamously a weight under the one wing; then under the other is atheism, the championed masquerade."
"The ratio of feed to flesh in chicken, the most efficient animal by this measure, is two pounds of corn to one of meat, which is why chicken costs less than beef."
"Where ignorance lurks, so too do the frontiers of discovery and imagination."
Explore more quotes by Marvin Minsky
"I heard that the same thing occurred in a scene in Alien, where the creature pops out of the chest of a crewman. The other actors didn't know what was to happen; the director wanted to get true surprise."
"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."
"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."
"Kubrick's vision seemed to be that humans are doomed, whereas Clarke's is that humans are moving on to a better stage of evolution."
"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."
"By the way, it was his simulations that helped out in Jurassic Park - without them, there would have been only a few dinosaurs. Based on his techniques, Industrial Light and Magic could make whole herds of dinosaurs race across the screen."
"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."
"Societies need rules that make no sense for individuals. For example, it makes no difference whether a single car drives on the left or on the right. But it makes all the difference when there are many cars!"
"Around 1967 Dan Bobrow wrote a program to do algebra problems based on symbols rather than numbers."
"Once when I was standing at the base, they started rotating the set and a big, heavy wrench fell down from the 12 o'clock position of the set, and got buried in the ground a few feet from me. I could have been killed!"
bottom of page