A simple linear regression example in TensorFlow(TM) is given at (https://www.tensorflow.org/tutorials/keras/basic_regression). By default, it produces none of the outputs of linear regression, other than MAE or MSE, on request through a print statement. Testing set Mean Abs Error: $2788.86 Time spent
I had my first exposure to programming in a FORTRAN class with real punchcards, back in the day, before I knew that GOTO was considered harmful. The exposure was brief and left me wondering whether Russian verbs of motion might not be easier to study, after all. In the years
The Federal Bureau of Investigation (FBI) has lead responsibilities for protecting the United States against domestic crimes initiated abroad. These responsibilities include protection against “covert actions by foreign governments to influence U.S. political sentiment or public discourse” (https://www.fbi.gov/investigate/counterintelligence/foreign-influence). It has illustrated its mission
I attended a nice Meetup last night, and one of the speakers quoted Turing’s description of a program able to modify its own instructions as a good description of artificial intelligence (AI) and another had a nifty typology relating all the standard tools in data science to their role
This post makes a trio with two most recent blogs on the same subject for R and Excel, this time in Python usking the sklearn package. The example given in the official documentation (https://goo.gl/GGmUKK) is somewhat sketchy and uses a different dataset than the previous two examples.
I was recently puzzling over an academic paper in the social sciences with a multiple linear regression model that seemed off. (Communication with the authors educated me on considerations that resolved my concerns.) During the course of my puzzling, I compared what I was seeing as model output in the
Two mysteries: Why were the data not stratified into a training set and a test set? How could temporal auto-correlation fail to be addressed?
As an analytic data scientist, I want to spend my time thinking about data and ways to extract useful information from them. I can’t do that if I’m spending hours trying to figure out why syntactically valid software won’t compile.
Combined with our innate over-perception of area and failing to weight voting results by percentage, we perceive a sea of red surrounding a few islands of blue.
Our tools may appear to work but then fail spectacularly
When you find the answer to a question you don’t understand, you can expect to see it again.
