jostmey / nakedtensor Goto Github PK

"There are a few conditions that the theory says are important, like the step size MUCH decrease with each iteration. For now, who cares! It works."

Should be

"There are a few conditions that the theory says are important, like the step size MUST decrease with each iteration. For now, who cares! It works."

Capitalization added to highlight typo

Thanks for setting this up. I am wondering the "bigdata.py". It appears to me the code does not use all the data from the "big data" population and only samples 8 points a time. That is no different than the "tensor.py" which just use the same 8 points over and over. Can you elaborate? Thanks.

No biggie, just wanna change w --> weights and b --> bias on lines 25, 26

This isn't an issue, but I did see that you responded to some other questions.

What if you had four features (four xs, as in the petal dataset)? How would your code change?

Sorry if this is am off the topic question, I am new to this.

I'd love to recommend this to folks, have you considered applying proper open source licensing on it? We release TF under Apache...