Difference between revisions of "Machine learning"
(Created page with "Machine learning is the idea of letting algorithms write (or update) their own codes. It is at the heart of recent breakthroughs in computer science, especially in image analy...") |
m |
||
| Line 4: | Line 4: | ||
The most compelling case for machine learning is arguably given in Section 7 of [[Turing 1950]] paper. | The most compelling case for machine learning is arguably given in Section 7 of [[Turing 1950]] paper. | ||
| + | |||
| + | [http://incompleteideas.net/IncIdeas/BitterLesson.html Sutton19] argues that this is indeed what we have been observing over the last few decades. Cleverly crafted algorithms for numerous tasks have been spectacularly outperformed by machine learning algorithms. | ||
| + | |||
| + | <blockquote>More data beats clever algorithms, but better data beats more data. (Peter Norvig)</blockquote> | ||
== Supervised, unsupervised and reinforced == | == Supervised, unsupervised and reinforced == | ||
Revision as of 12:04, 27 January 2020
Machine learning is the idea of letting algorithms write (or update) their own codes. It is at the heart of recent breakthroughs in computer science, especially in image analysis, speech recognition, natural language processing, but even problem solving [cite AlphaFold, deep learning for symbolic math]. Perhaps most crucially, there are strong arguments to suggest that it will allow further spectacular progress in the coming years.
Contents
Turing's argument
The most compelling case for machine learning is arguably given in Section 7 of Turing 1950 paper.
Sutton19 argues that this is indeed what we have been observing over the last few decades. Cleverly crafted algorithms for numerous tasks have been spectacularly outperformed by machine learning algorithms.
More data beats clever algorithms, but better data beats more data. (Peter Norvig)
Supervised, unsupervised and reinforced
There are 3 main forms of learning.
What makes machine learning safety hard
Can't apply formal verification!
Machine learning is data and goal-driven!
This means that we should care about quality data collection, but also on objective function design. It has been argued that the latter should follow the principle of alignment.
