LurkerAbove

I had an idea about explaining ML predictions without direct access to the data or the model: provide basic stats about your data, use them to generate synthetic data, then train a surrogate to predict your model's predictions on the synthetic data.

Could be handy for model risk management and governance, e.g. if you need a challenger model for SR 11-7 without all the hassle of getting access to the original data, getting the black box model set up, and so on. I wrote it because I remember having to create "throwaway" models to show why I needed a better model; it would have been nice to just make a couple of API calls instead.

SDK: https://github.com/proxyml/proxyml-sdk-python

Schema builder: https://github.com/proxyml/schema-builder

Landing page: https://proxyml.ai/

I had a recruiter contact me about a COBOL --> Java project a couple of weeks ago. I don't remember the $100/hour part though, seems like that would've stuck with me!

I don't have experience with medical ultrasound, but I have built a few basic ultrasonic systems around a PC or a single board computer for structural testing applications. If you're not doing phased array ultrasonics you can build a system for under $1000USD, possibly less if you can use PVDF instead of PZT. The expensive part is the software.

I've recently started reading the dead tree version of the newspaper and I've noticed that only do I seem to retain more of what I've read vs. reading the electronic version, for me it's something along the lines of a focus exercise. It really feels like it's clearing out the cobwebs.

If SEP IRAs as mentioned above aren't an option, HSAs might be worth considering - after 65 they aren't restricted to medical expenses. I-bonds might be an interesting component for future retirement as well.

Page loads on GL.com can take a while, but I wouldn't say that I've found the actual pull/push cycle to be slow per se. I'd describe it more like "measurable."

I used to more or less alternate between Github and Bitbucket but I've been using GitLab exclusively for the past six months. So far it's been a mostly painless transition. I've only had one hiccup, I had an IP banned for an hour or so but that's more Netbeans' fault than GitLab's .

Earlier this year I was working with an outfit that was on Java 4 for A Really Important Business Application. That said, they were looking at moving to IIRC 7 just as I was leaving.