“Despite the simplicity of the approach, we were surprised to find that the method was able to substantially outperform a number of existing approaches on popular few-shot image classification benchmarks, Omniglot and MiniImageNet2, including existing approaches that were much more complex or domain…”— Chelsea Finn, bair.berkeley.edu
“Scruffy Reasoning — I work in an imprecise world: I start with structured knowledge representations and classic algorithms, and then I generalize them to be more compatible with the incomplete and noisy data of the real world.”— Catherine Havasi, web.media.mit.edu
“These structures are crude and schematic, but as with most of the workings of gender and/or authority, the crude and schematic is usually all too apt.”— Jane Gallop, amazon.com
“You don’t need to understand the details of the message; it’s enough to get the gist of it by seeing which words it contains.”— Pedro Domingos, amazon.com
“If you try to come up with a set of rules that makes an exception, you’ll probably wind up with a worse answer than if you’d just ignored it. Learning a set of rules that gets [hyper-contextual instances] right is actually counterproductive: you’re better off ‘misclassifying’ it.”— Pedro Domingos, amazon.com
“As a rule of thumb, a dumb algorithm with lots and lots of data beats a clever one with modest amounts of it.”— Pedro Domingos, homes.cs.washington.edu
“Even if an exact solution is far beyond reach, a reasonable approximate solution is quite feasible.”— Steven Abney, cs.columbia.edu