Difference between revisions of "1838: Machine Learning"
(→The usage of "recurrent" seems explained well enough.) |
(Fleshed out the discussion of machine learning stuff to include more than just support vector machines.) |
||
| Line 12: | Line 12: | ||
Cueball stands next to what looks like a pile of garbage (or compost), with a Cueball-like friend standing atop it. The pile has a funnel (labelled "data") at one end and a box labelled "answers" at the other. Here and there mathematical matrices stick out of the pile. As the friend explains to the incredulous Cueball, data enters through the funnel, undergoes an incomprehensible process of linear algebra, and comes out as answers. The friend appears to be a functional part of this system himself, as he stands atop the pile stirring it with a paddle. His machine learning system is probably very inefficient, as he is integral to both the mechanical part (repeated stirring) and the learning part (making the answers look "right"). | Cueball stands next to what looks like a pile of garbage (or compost), with a Cueball-like friend standing atop it. The pile has a funnel (labelled "data") at one end and a box labelled "answers" at the other. Here and there mathematical matrices stick out of the pile. As the friend explains to the incredulous Cueball, data enters through the funnel, undergoes an incomprehensible process of linear algebra, and comes out as answers. The friend appears to be a functional part of this system himself, as he stands atop the pile stirring it with a paddle. His machine learning system is probably very inefficient, as he is integral to both the mechanical part (repeated stirring) and the learning part (making the answers look "right"). | ||
| − | The main joke is that, despite this description being too vague and giving no intuition or details into the system, it is close to the level of understanding most machine learning experts have of the | + | The main joke is that, despite this description being too vague and giving no intuition or details into the system, it is close to the level of understanding most machine learning experts have of the many techniques in machine learning. 'Machine learning' algorithms that can be reasonably described as pouring data into linear algebra and stirring until the output looks right include support vector machines, linear regressors, logistic regressors, and neural networks. Major recent advances in machine learning often amount to 'stacking' the linear algebra up differently, or varying stirring techniques for the compost. <!--''(Replaced reference to neural networks, but still needs explanation of vector machines.)''--> <!-- Dear previous comment-leaver: having geeked out moderately hard on neural network trivia for the last year or so, I regret to inform you that Randall's description also applies to neural networks. Most 'big advances' in neural networks are just stacking the linear algebra differently or adding different functions between them, you're still just pouring data onto linear algebra and stirring until the answers look right. Am changing to reflect that.> |
====Composting==== | ====Composting==== | ||
Revision as of 05:20, 27 July 2020
| Machine Learning |
 Title text: The pile gets soaked with data and starts to get mushy over time, so it's technically recurrent. |
Explanation
Machine learning is a method employed in automation of complex tasks. It usually involves creation of algorithms that deal with statistical analysis of data and pattern recognition to generate output. The validity/accuracy of the output can be used to give feedback to make changes to the system, usually making future results statistically better.
Cueball stands next to what looks like a pile of garbage (or compost), with a Cueball-like friend standing atop it. The pile has a funnel (labelled "data") at one end and a box labelled "answers" at the other. Here and there mathematical matrices stick out of the pile. As the friend explains to the incredulous Cueball, data enters through the funnel, undergoes an incomprehensible process of linear algebra, and comes out as answers. The friend appears to be a functional part of this system himself, as he stands atop the pile stirring it with a paddle. His machine learning system is probably very inefficient, as he is integral to both the mechanical part (repeated stirring) and the learning part (making the answers look "right").
The main joke is that, despite this description being too vague and giving no intuition or details into the system, it is close to the level of understanding most machine learning experts have of the many techniques in machine learning. 'Machine learning' algorithms that can be reasonably described as pouring data into linear algebra and stirring until the output looks right include support vector machines, linear regressors, logistic regressors, and neural networks. Major recent advances in machine learning often amount to 'stacking' the linear algebra up differently, or varying stirring techniques for the compost.
