Publications by jmount
abs and relu are not Mercer Kernels
I am sharing some rough notes (in R and Python) here on how while dot(a, b) fulfills “Mercer’s condition” (by definition!, and I’ll just informally call these beasts a “Mercer Kernel”), the seemingly harmless variations abs(dot(a, b)) relu(dot(a, b)) are not Mercer Kernels (relu(x) = max(0, x) = (abs(x) + x)/2). It turns out they fail...
2063 sym
The Nature of Overfitting
Introduction I would like to talk about the nature of supervised machine learning and overfitting. One of the cornerstones of our data science intensives is giving the participants the experiences of a data scientist in a safe controlled environment. We hope by working examples they can quickly get to the point where they have experience that can...
16016 sym R (10432 sym/44 pcs) 10 img 1 tbl
The Nature of Overfitting
Introduction I would like to talk about the nature of supervised machine learning and overfitting. One of the cornerstones of our data science intensives is giving the participants the experiences of a data scientist in a safe controlled environment. We hope by working examples they can quickly get to the point where they have experience that can...
16021 sym R (10432 sym/44 pcs) 10 img 1 tbl
Smoothing isn’t Always Safe
Introduction Here is a quick data-scientist / data-analyst question: what is the overall trend or shape in the following noisy data? For our specific example: How do we relate value as a noisy function (or relation) of m? This example arose in producing our tutorial “The Nature of Overfitting”. One would think this would be safe and easy to a...
6370 sym R (3827 sym/25 pcs) 26 img
Smoothing isn’t Always Safe
Introduction Here is a quick data-scientist / data-analyst question: what is the overall trend or shape in the following noisy data? For our specific example: How do we relate value as a noisy function (or relation) of m? This example arose in producing our tutorial “The Nature of Overfitting”. One would think this would be safe and easy to a...
6370 sym R (3827 sym/25 pcs) 26 img
Variable Utility is not Intrinsic
There is much ado about variable selection or variable utility valuation in supervised machine learning. In this note we will try to disarm some possibly common fallacies, and to set reasonable expectations about how variable valuation can work. Introduction In general variable valuation is estimating the utility that a column of explanatory valu...
9015 sym R (2372 sym/23 pcs) 4 tbl
Variable Utility is not Intrinsic
There is much ado about variable selection or variable utility valuation in supervised machine learning. In this note we will try to disarm some possibly common fallacies, and to set reasonable expectations about how variable valuation can work. Introduction In general variable valuation is estimating the utility that a column of explanatory valu...
9015 sym R (2372 sym/23 pcs) 4 tbl
Code for the “Variable Utility is not Intrinsic” Article
I’ve now shared the code for my “Variable Utility is not Intrinsic” article here: https://github.com/WinVector/Examples/tree/main/Variable_Utility_is_not_Intrinsic. And I have also ported the entire article to Python. It is actually kind of neat to be able to compare the two and see how close doing data science in R and in Python can be ma...
752 sym
Code for the “Variable Utility is not Intrinsic” Article
I’ve now shared the code for my “Variable Utility is not Intrinsic” article here: https://github.com/WinVector/Examples/tree/main/Variable_Utility_is_not_Intrinsic. And I have also ported the entire article to Python. It is actually kind of neat to be able to compare the two and see how close doing data science in R and in Python can be ma...
752 sym
Bilingual Data Science
I’d like to share a new talk on bilingual data science. It is limited to R and Python, so it is a bit of a “we play all kinds of music, both Country and Western.” It has what I feel is a really neat example how I used Jetbrains Intellij PyCharm to quickly translate an R .Rmd file to a Python Juptyter Lab .ipynb notebook. The translation is ...
869 sym