38
12
Inspired by the job-interview with Joel Grus, the goal of this challenge is to write a tensorflow (or other deep/machine learning) program that learns Fizzbuzz and correctly prints out the answers to the positive integers less than 1000.
You can assume there are files named train.csv
and test.csv
and each contain a sorted list of sequential integers and the fizzbuzz answer:
...
100, buzz
101, 101
102, fizz
103, 103
104, 104
105, buzz
...
150000, fizzbuzz
test.csv
spans 1-1000 and train.csv
spans 1001-150000.
Rules
- You must not hard-code the rules to Fizzbuzz anywhere in your program. The output must be from a machine learned representation that is learned while running the code.
- You must utilize
train.csv
in the training set and check your output againsttest.csv
. You cannot usetest.csv
during training. - You must get all outputs correct from
test.csv
(but as is case with deep-learning, we'll allow your code to fail this rule no more than 5% of the time). - You may use any language and any external module (eg. python/tensorflow) as long they explicitly perform some kind of learning. Reference both the language and the module in the title of your post.
- This is a popularity contest, so the submission with the most votes after one week wins.
3
Hi Hooked, welcome to the site! I'd encourage you to try using the sandbox before posting a challenge next time, since you probably would have been advised to avoid a popularity contest. Right now, we're in an awkward stage where popularity contests are still technically allowed, but frowned upon, and hard to do right (especially for new users). One thing that might attract downvotes on this question is that it's asking to solve a task in a very specific way, which is cautioned against in the tag wiki.
– James – 2016-05-24T04:41:10.5803Thanks for the info @DrGreenEggsandHamDJ. I'm a long time lurker and I tried to model this off of previous questions (without knowledge of the transition). Re restrictions: there are many creative ways to solve this problem (the type of NN isn't enforced). If it gets downvoted I'll understand and pack this one up, but I'm really looking forward to see what comes out of this! (I don't think there are any deep learning codegolf.SE questions at all) – Hooked – 2016-05-24T05:13:59.510
Not all machine learning algorithms are "Deep Learning", so I don't really see what it has to do with the challenge. – Fatalize – 2016-05-24T06:28:52.057
3Where can we find
train.csv
andtest.csv
? What is the validity criterion? – flawr – 2016-05-24T08:28:39.977What's the representation of the input and nonlinear functions that are allowed? There are trivial answers if you don't constraint these... – Memming – 2016-05-24T11:47:01.403
1
Here's an example of a good machine learning question: http://codegolf.stackexchange.com/questions/44707/lab-rat-race-an-exercise-in-genetic-algorithms
– durron597 – 2016-05-24T17:45:19.903