Optuna: An open source hyperparameter optimization framework to automate hyperparameter search
- Medium writeup. It looks like this is Bayesian, and is better than hyperopt?
7:00 – 5:00 ASRC GOES
- Starting to add Wayne’s comments
- Finished the intro, starting motivation
- NSOF Meeting with Isaac & Bruce
- Still looking at the optimal scenario to use the current simulators (running over a weekend) to generate data
- Data sets are used to train and evaluate, then progressively simplified until they can no longer recognize the source data. This will let us estimate the fidelity of the simulations we need.
- JuryRoom meeting. Looking into adding UX faculty. Meeting is expanding to 6:00 – 8:00
ASRC GOES 7:00 – 4:30, 6:30 – 7:00
- Write up something for Erik and John?
- Send gdoc link to Bruce – done
- apply for TF Dev invite – done
- Schedule physical! – done
- Dissertation – more Designing for populations
- Comment EvolutionaryOptimizer – almost done
- Comment ModelWriter
- User’s guide
- Comment the excel utils?
- Waikato meeting with Alex and Panos
City Arts & Lectures: Privacy and Technology
- This week, a conversation about privacy, ethics, and organizing in the world of technology.Who benefits from the lack of diversity in the tech industry? Does artificial intelligence reflect the biases of those who create it? How can we push for regulation and transparency? These are some of the questions discussed by our guests, Meredith Whittaker, co-founder of AI Now at NYU and the founder of Google’s Open Research Institute; and Kade Crockford, Director of the ACLU Massachusetts’ Technology and Liberty Program. They appeared at the Sydney Goldstein Theater in San Francisco on June 7, 2019.
7:00 – 8:00 ASRC GOES
- Printed out some business cards for JuryRoom
- Antonio has submitted the manuscript – created a TAAS account and verified that its there
- Finished 0.5 pass at chapter 1!
- Goddard today
- See if I can get a permanent card? Done!
- More control system work
- Meeting with Wayne
- Send the as-delivered TAAS paper and cover letter. Done
- Work on getting the ML/Weapons paper reformatted tomorrow
- Send chapter one of the dissertation
- I’ll then start sending the chapters as I “complete” them, and we’ll see how it’s going. If the dissertation seems to be coming together well, then we might switch strategies to a from a content-centric to a coherence-centric approach.
Trump, Qanon and an impending judgment day: Behind the Facebook-fueled rise of The Epoch Times
By the numbers, there is no bigger advocate of President Donald Trump on Facebook than The Epoch Times. The small New York-based nonprofit news outlet has spent more than $1.5 million on about 11,000 pro-Trump advertisements in the last six months, according to data from Facebook’s advertising archive — more than any organization outside of the Trump campaign itself, and more than most Democratic presidential candidates have spent on their own campaigns. Those video ads — in which unidentified spokespeople thumb through a newspaper to praise Trump, peddle conspiracy theories about the “Deep State,” and criticize “fake news” media — strike a familiar tone in the online conservative news ecosystem. The Epoch Times looks like many of the conservative outlets that have gained followings in recent years.
7:00 – 4:00 ASRC GOES
- I just found out that the UMBC, UMD, and TSU are Jan 2 – 22. I’ll be doing my defense in there somewhere
- Working on the TACJ section
- Add controllers for the reaction wheels so that a “go to AZ=30, EL=20, R= -10” can work
- Getting close:
- Next task is to subclass the ReactionWheelController to pitch, roll, and yaw controllers, so that they can manipulate their data separately
- Voltage should control the velocity and direction of the wheel
- Simulator can be told to add drag to a wheel
- I think Communications of the ACM is the next place to try the AI Weapons paper. It’s 5,000-ish words, so it looks like it should fit:
- Finished TAAS article and letter. Notified Antonio
ASRC GOES 7:00 – 4:00
- Adding the journalism framing example to the introduction
- Continue to work all data transfers into the Data Dictionary so that effective, tagged training in the sim can happen
- done-ish? Need to do another layer and figure out how to set up the command and response buffers – done
Data Dictionary as a spreadsheet