This is interesting:
"Automatically selects from several available machine learning techniques"
So not only does it learn, it's learning which learning techniques work best for different problems.
Google Prediction API
81–88 of 88 posts
Re: Google Prediction API
#82This is easily the most interesting announcement so far. Machine learning has so many applications, but its use is constrained by the high barriers to entry. Recommendation engines, for example, are huge sales drivers, but few among even the largest ecommerce stores use them. A simple prediction interface that's built on the ML expertise at Google is a win for everyone.
Directed Edge, a promising YC startup, makes recommendation engines surprisingly easy: http://www.directededge.com/ It's quite a bit higher-level than what Google is offering here, with all the benefits and drawbacks that entails.
If I have a graph of customers and what products they've bought, Directed Edge makes it easy to figure out what products to recommend to each customer. Generating the same recommendations with Google's prediction API is not as obvious to me. What data do you train it with? The nth product the customer bought as the output, and the 1..n-1th products as the input?
Maybe I'm slow, but I don't see how google's prediction API is a good replacement for collaborative filtering type recommendation engines.
Re: Google Prediction API
#83This is easily the most interesting announcement so far. Machine learning has so many applications, but its use is constrained by the high barriers to entry. Recommendation engines, for example, are huge sales drivers, but few among even the largest ecommerce stores use them. A simple prediction interface that's built on the ML expertise at Google is a win for everyone.
The graphic on the front page would be more impressive if the input was "french" and the output was the specific phrase :)
Re: Google Prediction API
#84Are there any (preferably FOSS) libraries that does anything like this?
In Python there is a wonderful library called the Natural Language Toolkit (NLTK) available free and open source at http://www.nltk.org/ . With NLTK you can build classifiers, decision trees, and train/predict with bayesian classifiers similarly to Google's Prediction API examples. It's pretty easy to get started, and it's code that you run locally, so there is no network traffic. I use it on http://www.protopub.com…
Python's Reverend Thomas library is a naive Bayes classifier library. You can do the language guessing and other basic classifications with it: http://divmod.org/trac/wiki/DivmodReverend
Re: Google Prediction API
#85Earlier quoted context omitted.
The point is that they took a large number of documents, which are clearly labelled as to language, gave it as a training set to the machine, and they now have a classifier that lets you input random text and tells you the language it was probably written in. In principle you can do this with any data set and any set of discrete outcomes. In general, though, you should expect that the resulting classifier won't give…
they now have a classifier that lets you input random text and tells you the language it was probably written in. Incidentally, Google Translate does this and starts guessing the source language as you start typing. I found it interesting that when you type a single character, w is guessed as Polish, i is Norwegian, s is Czech, e is Portuguese...
Frequency of first-character of words in those languages.
Re: Google Prediction API
#86Not enough details available on how it works. Would rather build my own at this point. Plus the way this is billed oversimplifies the whole model design process. Sorry to sound so negative, but I just earned a PhD in Machine Learning. How would you feel if you were replaced by an API? :-(
trust me, you have nothing to worry about. Us noobs with regular bachelor degrees who use this will get into trouble because we can't understand the results and the math is all over our heads. We still need you PhD's...(gives T_S_ a hug)
Re: Google Prediction API
#87Re: Google Prediction API
#88Not enough details available on how it works. Would rather build my own at this point. Plus the way this is billed oversimplifies the whole model design process. Sorry to sound so negative, but I just earned a PhD in Machine Learning. How would you feel if you were replaced by an API? :-(
trust me, you have nothing to worry about. Us noobs with regular bachelor degrees who use this will get into trouble because we can't understand the results and the math is all over our heads. We still need you PhD's...(gives T_S_ a hug)
Thanks man, sniffle.
Actually I'm not too worried about that. More worried that the guys at google are waaaay smarter than me :-)