So you wanna try Deep Learning?

therobot24 11 years ago |

"Always answer 'Do you want more data?' with 'Yes, please.'" -- ehhh more data isn't necessarily "Good" Data, there are hundreds of MTurk collection studies to verify the old phrase "Garbage in, Garbage out"

dagw 11 years ago | |

You can always ignore data that you have, but you can't use data that you don't have.

geekingfrog 11 years ago | | |

Be careful about spending resources on collecting useless data though.

dagw 11 years ago | | |

That is a very good point. If you have data lying around, you might as well take a look at it, but think two and three times before you spend time and money collecting new data.

therobot24 11 years ago | | |

this is more what i'm getting at - collecting more data is good, but just having more data isn't necessarily 'good'

spullara 11 years ago |

The Java library Encog (https://github.com/encog) has a huge number of features out of the box for building neural networks.

pinkyand 11 years ago |

BTW ersatz has recently started to offer a deep learning cloud service, which it claims is very easy to use. Has anybody used it ? how is it ?

dhagz 11 years ago |

Is anyone else seeing `[Math Processing Error]` in big red italics at random points?

Houshalter 11 years ago | |

I just get a bunch of $ symbols around the math parts.