explain xkcd - User contributions [en]

1838: Machine Learning

2017-05-17T05:12:33Z

1I1III1: recursive --> recurrent. oops

{{comic
| number = 1838
| date = May 17, 2017
| title = Machine Learning
| image = machine_learning.png
| titletext = The pile gets soaked with data and starts to get mushy over time, so it's technically recurrent.
}}

==Explanation==
{{incomplete|Created by a BOT - Please change this comment when editing this page. Do NOT delete this tag too soon.}}

This comic satirizes machine learning, more specifically neural networks. In it's most basic form, a neural network takes data and results and strengthens connections that give the right answer and weakens ones that don't, until the results "look right". Neural networks are extremely data dependent, and make remarkably few guarantees when compared to most other computing techniques, thus the joke.

Recently, other forms of neural networks, such as LSTMs, feed old sequence data back into the network with some delay, making it recurrent. The title text calls this the pile "getting mushy".

==Transcript==
{{incomplete transcript|Do NOT delete this tag too soon.}}

<i>This</i> is your machine learning system?

Yup! You pour the data into this big pile of linear algebra, then collect the answers on the other side.

What if the answers are wrong?

Just stir the pile until they start looking right.

{{comic discussion}}

1838: Machine Learning

2017-05-17T05:11:07Z

1I1III1: added some basics about machine learning

{{comic
| number = 1838
| date = May 17, 2017
| title = Machine Learning
| image = machine_learning.png
| titletext = The pile gets soaked with data and starts to get mushy over time, so it's technically recurrent.
}}

==Explanation==
{{incomplete|Created by a BOT - Please change this comment when editing this page. Do NOT delete this tag too soon.}}

This comic satirizes machine learning, more specifically neural networks. In it's most basic form, a neural network takes data and results and strengthens connections that give the right answer and weakens ones that don't, until the results "look right". Neural networks are extremely data dependent, and make remarkably few guarantees when compared to most other computing techniques, thus the joke.

Recently, other forms of neural networks, such as LSTMs, feed old sequence data back into the network with some delay, making it recursive. The title text calls this the pile "getting mushy".

==Transcript==
{{incomplete transcript|Do NOT delete this tag too soon.}}

<i>This</i> is your machine learning system?

Yup! You pour the data into this big pile of linear algebra, then collect the answers on the other side.

What if the answers are wrong?

Just stir the pile until they start looking right.

{{comic discussion}}

Talk:1826: Birdwatching

2017-04-19T05:42:35Z

1I1III1:

This is a big one.[[Special:Contributions/108.162.246.41|108.162.246.41]] 04:07, 19 April 2017 (UTC)

I wonder if the size is a technical error, or if I am missing some subtle joke. [[Special:Contributions/108.162.245.184|108.162.245.184]] 04:37, 19 April 2017 (UTC)

I guess it's the latter. [[Special:Contributions/162.158.166.71|162.158.166.71]] 04:39, 19 April 2017 (UTC)

I think the vacuum is a further joke about scale and distance playing on the absurdity of trying to vacuum from a range of one mile. I must say I don't really understand this comic very well.[[Special:Contributions/108.162.245.70|108.162.245.70]] 04:47, 19 April 2017 (UTC)

I thought the vacuum was trying to drain the atmosphere to make it so that the birds can't fly as high.[[User:1I1III1|1I1III1]] ([[User talk:1I1III1|talk]]) 05:42, 19 April 2017 (UTC)