Category Archives: Conferences

Phil 8.13.20

Ride through the park today and ask about pavilion rental – done

Māori Pronunciation

Iñupiaq (Inupiatun)

GPT-2 Agents

  • Rewrite intro, including the finding that these texts seem to be matched in some way. Done
  • Uploaded the new version to ArXiv. Should be live by tomorrow
  • Read Language Models as Knowledge Bases, and added to the lit review.
  • Discovered Antoine Bosselut, who was lead author on the following papers.Need to add them to the future work section
    • Dynamic Knowledge Graph Construction for Zero-shot Commonsense Question Answering
      • Understanding narratives requires dynamically reasoning about the implicit causes, effects, and states of the situations described in text, which in turn requires understanding rich background knowledge about how the social and physical world works. At the core of this challenge is how to access contextually relevant knowledge on demand and reason over it.
        In this paper, we present initial studies toward zero-shot commonsense QA by formulating the task as probabilistic inference over dynamically generated commonsense knowledge graphs. In contrast to previous studies for knowledge integration that rely on retrieval of existing knowledge from static knowledge graphs, our study requires commonsense knowledge integration where contextually relevant knowledge is often not present in existing knowledge bases. Therefore, we present a novel approach that generates contextually relevant knowledge on demand using generative neural commonsense knowledge models.
        Empirical results on the SocialIQa and StoryCommonsense datasets in a zero-shot setting demonstrate that using commonsense knowledge models to dynamically construct and reason over knowledge graphs achieves performance boosts over pre-trained language models and using knowledge models to directly evaluate answers.
    • COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
      • We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.


  • 10:00 sim status meeting – planning to fully evaluate off-axis rotation by Monday, then characterize Rwheel contribution, adjust the control system and start commanding vehicle rotations by the end of the week? Seems ambitions, but what the hell.
  • 2:00 status meeting
  • Anything about GVSETS? Yup: Meeting Wed 9/16/2020 9:00 AM – 10:00 AM


  • 5:30 meeting. Discuss proposal and additional meetings


  • Transfer more content

Phil 8.11.20

Zero-Shot Learning in Modern NLP

  • In this post, I will present a few techniques, both from published research and our own experiments at Hugging Face, for using state-of-the-art NLP models for sequence classification without large annotated training sets.

Found a really good dashboard for US economic indicators:



  • I think I realize my problem about the second axis. It’s not rotating around the origin, so the vectors that I’m using to create the rotation vectors are not right.
  • Fixed! Here are some rotations (180 around Z, 90 around x, and 360 around z, 180 around x)

GPT-2 Agents

  • I did 11 runs of S/He walked into the room and made word clouds:
  • I’m going to re-run this on my GPT-2 so I can have a larger N. Just need to do some things to the test code to output to a file


  • Finished the last review. The last paper was an ontological model with no computation in it
  • Uploaded and finished!

ML seminar

  • I have access to the Twitter data now. Need to download and store it in the db
  • Presentation next week

Phil 7.30.20

GPT-2 Agents

  • Writing up graph creation


  • More coordinate transforms. I think a good way to do this is to determine the desired target vector, take the cross product of that with the current vector and use that as the axis of rotation. Recalculate each frame to keep the rotations on track
  • Think I got the hang of the quaternions for the target frame. I need to put things together in a nice class:



  • Sent Shimei a note about online CHI experiences in the current issue of  Interactions
  • Start writing review


  • 5:30 Meeting tonight

Phil 7.20.20

My guess it that barring interference of some kind all US cities will have something like what’s going on in Portland by election day

GPT-2 Agents

  • Back from break, and thinking about what to do next. I think the first thing to do is simply gather more data from the model. Right now I have about  1,500 GPT-2 moves and about 190,000 human moves. Increasing the number of predictions to 1,000 by adding a batch size value. Otherwise I got out-of-memory errors.
  • I had started the run in the morning and was almost done when a power failure hit and the UPS didn’t work. Ordered a new UPS. Tried to be clever about finishing off the last piece of data but left in the code that truncated the table. Ah, well. Starting over.
  • Next is to adjust the queries so that the populations are more similar. The GPT-2 moves come from the following prompts:
    probe_list = ['The game begins as ', 'In move 10', 'In move 20', 'In move 30', 'In move 40', 'White takes black ', 'Black takes white ', 'Check. ']

    That means I should adjust my queries of the human data to reflect those biases, something like:

    select * from table_actual where move_number = 1 order by move_number limit 50;

    which should match the probe ‘The game begins as ‘.

  • I’d also like to run longer, full games (look for ‘resigns’, ‘draw’, or ‘wins’) and parse them, but that’s for later.
  • Need to figure out the statistics to compare populations. I think I’m going to take some time and look through the NIST Engineering Statistics Handbook



  • Vadim seems to have made progress. Need to set up a meeting to chat and catch up
  • 2:00 meeting with V & E. Good progress!
  • GVSETS has been moved to Nov 3. Speaking of which, I’ll need to compare simulated and actual maneuvers, so stats here too. Now that the moves are cooking I’ll start on the stats


Phil 6.23.20

Oh, look, we’re not going to let smart, motivated people into the country and sabotage our future because, I dunno, being xenophobic trumps everything?

Collective Intelligence 2020

  • You can watch all the keynotes on our YouTube channel.
  • Conference proceedings (papers & presentations) are online here.

GPT-2 Agents

  • Working on getting Gephi installed and running everywhere.
  • Next is  to export graphs from networkx. Done! A little tricky. I’m using a dictionary attached to each node to store the pieces that traversed that particular edge, but the exporter chokes on that. So I have to create a new graph without the dict and export that. It looks pretty good too!


  • I’m going to import that into Illustrator and see if I can build a (distorted) chessboard. Here’s the result:


  • To get a sense of how this relates back to the ground truth of the chessboard, the red lines are the columns of the board (a – h) and the green lines are the rows (1 – 8). Here’s the comparison with the actual board:


  • It’s clearly a grid. The opposite corners are far away from each other. The left (queen) side of the board is more complicated, which may be because of the queen?
  • I had a chat with Aaron about all of this and I think the next step is to show that this map can be used for meaningful navigation. Consider the following two trajectories from opposite sides of the map:


  • These are the kind of trajectories that you’d like to be able to plot on a map. Let’s say you’re on square A1, and you’re on a rook. For you, only row 1 and column A are directly accessible. But maybe you could ride a bishop from A3 to F8, then take a king the rest of the way. Now, the shortest number of moves could be to take the rook from A1 to A8 to H8, but the journey would cover a greater distance. In terms of belief space, you would not be making incremental shifts to your understanding, you would be making two, equally large jumps that combined are roughly 1.4 times farther than the more direct route. That’s the difference between navigating in space vs navigating in a network.
  • I think the next step is to write an app that reads in the GEFX files, which contain location information and link them back to the database, so it’s possible to plot a beginning and an ending, and have the app figure out the legal moves that move you near that line towards your destination.
  • After that, it’s time to finetune the NN on the antibubbles corpora and see if the same thing can be done.


  • Need to record a video of my talk for GVSETS
  • Sent a copy to Aaron for SBIR
  • Started looking at the SBIR materials

ML Seminar

Phil 6.22.20

Cornell University was having a sale, so I got a book:

Mental Territories

  • Rarely recognized outside its boundaries today, the Pacific Northwest region known at the turn of the century as the Inland Empire included portions of the states of Washington and Idaho, as well as British Columbia. Katherine G. Morrissey traces the history of this self-proclaimed region from its origins through its heyday. In doing so, she challenges the characterization of regions as fixed places defined by their geography, economy, and demographics. Regions, she argues, are best understood as mental constructs, internally defined through conflicts and debates among different groups of people seeking to control a particular area’s identity and direction. She tells the story of the Inland Empire as a complex narrative of competing perceptions and interests.


  • Change the code so that there is a 30 day prediction based on the current rates regardless of trend. I think it tells the story of second waves better:


GPT-2 Agents

  • The ACSOS paper was rejected, so this is now the only path going forward for mapmaking research.
  • Used the known_nearest to produce a graph:
  • The graph on the left is the full graph, and the right is culled. First, note that node c is not in the second graph. There is no confirming link, so we don’t know if it’s an accident. Node e is also not on the chart, because it has no confirming link back through any 2-edge path.
  • Ok, I tried it for the first time on the chess data. There is a bug where [a-h] and [1-8] are showing up as nodes that I have to figure out. But they show up in the right way! Orthogonal and in order!


  • The bug seems to be in the way that List.extend() works. It seems to be splitting the string (which is a List, duh), and adding those elements as well? Nope, just doing one nesting too many
  • Ok, here are the first results. The first image is of all neighbors. The second is of only verified nearest neighbors (at least one edge chain of 2 that lead back to the original node)



  • In both cases, the large-scale features of the chessboard are visible. There is a progression from 1 to 8, and a to h. It seems clearer to me in the lower image, and the grid-like nature is more visible. I think I need to get the interactive manipulation working, because some of this could be drawing artifacts
  • Trying out the networkx_viewer. A little worried about this though:


  • And rightly so:


  • Going to try cloning and fixing. Nope. It is waaaaaaayyyyyy broken, and depends on earlier version of networkx
  • Networkx suggests Gephi, and there is a way to export graphs from networkx. Trying that
  • Seems usable?



  • Kind of stuck. Waiting on Vadim
  • Probably will be working on a couple of SBIRs for the next few weeks

Phil 6.18.20

Hotel reservations!

Sent a ping to Don about a paper to review

GPT-2 Agents

  • Started on common neighbor algorithm. Definitely a good place for recursion
  • Generating larger file



  • If you look at the center of the plot and squint a bit, you can see a bit of the grid:


  • There is an error: The string ‘, White moves pawn from h3 to g4. White takes black pawn. LCZero v0.24-sv-t60-3010 moves black knight from h5 to g7. White moves pawn from g4 to h5. LCZero v0.24‘ is parsing incorrectly due to the truly bizarre name (The little known Grand Master LCZero v0.24-sv-t60-3010). Need to fix the regex. I think I just need to make it so that there has to be a space in front and a space/period after.


  • Readthrough of GVSETS paper
  • 2:00 Meeting


  • Alex had a really good insight in that groups that are working at coming to consensus use terms to discuss their level of agreement that are independent of the points being argued. That’s could really be important in text analysis.

Phil 6.12.20

Hey! My dissertation is online now!

Optimizing Multiple Loss Functions with Loss-Conditional Training

  • The idea behind our approach is to train a single model that covers all choices of coefficients of the loss terms, instead of training a model for each set of coefficients. We achieve this by (i) training the model on a distribution of losses instead of a single loss function, and (ii) conditioning the model outputs on the vector of coefficients of the loss terms. This way, at inference time the conditioning vector can be varied, allowing us to traverse the space of models corresponding to loss functions with different coefficients

GPT-2 Agents

  • Applied to get on the OpenAI API waitlist
  • Started figuring out igraph. Welp, it doesn’t plot because cannot load library ‘libcairo-2.dll’: error 0x7e Diesn’t seem to be a good fix. It’s a shame, because igraph seems to be great for analyzing graphs mathematically. Removing everything
  • Looks like I can use networkx combined with networkx_viewer (pypi)(github). Look into that next. Upgraded from 2.1 to 2.4
  • Pulled my class over from Antibubbles and verified that it still works!



  • Send Jason my download code
  • Work on GVSETS paper
    • Added formatting changes and moved footnotes to citations
    • Adding a figure for the pipeline. Hmmm. It’s um… big


Phil 6.10.20

Finish ACSOS review

GPT-2 Agents

  • Generate embeddings
    • Trying running much longer sequences (max_length = 1000). The lets games run long enough  that they often conclude (the term “resigns”, “wins”, or “draw occurs in the text)
    • Put together a simple regex ‘[a-h][1-8]’ that pulls out all the squares in sequence from a game
    • Extracting game square sequences to create files that will feed into Word2Vec. The class is started and most of the issues are worked out. I added a check for game endings so beginning and endings are not place together oddly.
    • Here’s the trimmed input text
      The game begins as white uses the Sicilian opening. and black countering with Najdorf, Adams attack. Loek Van Wely moves white pawn from e2 to e4. Black moves pawn from c7 to c5. In move 2, White moves knight from g1 to f3. Black moves pawn from d7 to d6. White moves pawn from d2 to d4. Black moves pawn from c5 to d4. Black takes white pawn. White moves knight from f3 to d4. White takes black pawn. Black moves knight from g8 to f6. In move 5, White moves knight from b1 to c3. Arseniy Nesterov moves black pawn from a7 to a6. Loek Van Wely moves white bishop from c1 to e3. Black moves pawn from e7 to e6. In move 7, White moves pawn from f2 to f4. Black moves knight from b8 to d7. White moves queen from d1 to d2. Black moves pawn from b7 to b5. Loek Van Wely queenside castles. Black moves bishop from f8 to e7. White moves bishop from f1 to d3. Arseniy Nesterov kingside castles. White moves king from c1 to b1. Black moves rook from a8 to b8. White moves pawn from g2 to g3. Black moves queen from d8 to a5. Loek Van Wely moves white king from b1 to a1. Black moves bishop from e7 to d6. Black takes white knight. Loek Van Wely moves white bishop from d3 to e4. White takes black pawn. Black moves rook from b8 to b2. Black takes white pawn. In move 17, White moves bishop from e4 to h7. White takes black pawn. Check. Arseniy Nesterov moves black king from g8 to h8. White moves bishop from h7 to d3. Black moves bishop from d6 to f4. Black takes white pawn. Check. In move 19, White moves bishop from e3 to f4. White takes black bishop. Black moves rook from b2 to f2. White moves rook from h1 to f1. Black moves knight from d7 to e5. White moves queen from d2 to e2. Black moves queen from a5 to d2. In move 22, White moves knight from c3 to e2. White takes black queen. Black moves rook from f2 to e2. Black takes white knight. Loek Van Wely moves white bishop from f4 to e3. Black moves rook from e2 to e3. Black takes white bishop. White moves pawn from f4 to f5. Black moves rook from f8 to d8. White moves pawn from a2 to a4. Arseniy Nesterov moves black bishop from c8 to b7. White moves pawn from a4 to a5. Arseniy Nesterov moves black bishop from b7 to c8. White moves pawn from a5 to b6. White takes. Arseniy Nesterov moves black pawn from a6 to b5. Black takes white pawn. White moves queen from e2 to b5. White takes black pawn. Black moves knight from e5 to c4. White moves pawn from h2 to h3. Black moves knight from c4 to a5. In move 30, Loek Van Wely moves white queen from b5 to a4. Arseniy Nesterov moves black pawn from h7 to h6. White moves bishop from d3 to b1. Black moves rook from d8 to d1. Check. Loek Van Wely
    • And here’s the sequence
      e2 e4 c7 c5 g1 f3 d7 d6 d2 d4 c5 d4 f3 d4 g8 f6 b1 c3 a7 a6 c1 e3 e7 e6 f2 f4 b8 d7 d1 d2 b7 b5 f8 e7 f1 d3 c1 b1 a8 b8 g2 g3 d8 a5 b1 a1 e7 d6 d3 e4 b8 b2 e4 h7 g8 h8 h7 d3 d6 f4 e3 f4 b2 f2 h1 f1 d7 e5 d2 e2 a5 d2 c3 e2 f2 e2 f4 e3 e2 e3 f4 f5 f8 d8 a2 a4 c8 b7 a4 a5 b7 c8 a5 b6 a6 b5 e2 b5 e5 c4 h2 h3 c4 a5 b5 a4 h7 h6 d3 b1 d8 d1


    • I can do other things like split into white and black, but that’s pretty tricky and I don’t think it’s worth it
  • Start building networks. Here are some api possibilities


  • If the devlab is still up, work on pulling down data. Nope, the VPN is working so badly today that I can’t even load my webmail
  • Going to work on the download and transfer using my local Influx – done!


Complete copy of remote data on local server

  • 2:00 Meeting

Phil 6.1.20


It’s all been a bit much recently, so yesterday I took advantage of the wonderful weather and went on a long ride with a few friends.

D20 – Nagged Zach with this image. He responses generally were “It is generally pretty optimistic around here”, and “According to google is is getting better. I wonder where their data comes from”.


GPT-2 Agents

  • Still some debugging. added output of the raw move files to find games better
  • Dates aren’t right either – fixed
  • Added some better triggering of the print_board method
  • WOW! I mean it shouldn’t be that surprising, but the pgn is wrong. Going to add a flag for games with problem moves. Then I think I should be able to generate text.


  • Put paper in the right format (word?)
  • Create the slides. Verify the speaking duration – done. It’s 20 minuts, I think probably 15 for talk and 5 for questions
  • Found the technical paper repo. Looks like I didn’t have to worry about length!
  • Uploaded! Just use the info in the email from GVSETS Tech Session Admin

Google is profiting from dozens of websites that peddle hoaxes and conspiracy theories about Covid-19, according to a Tech Transparency Project (TTP) investigation, revealing a major hole in the company’s claims that it’s fighting misinformation about the pandemic.


Phil 5.7.20


  • Everything is silent again.

GPT-2 Agents

  • Continuing with PGNtoEnglish
    • Building out move text
    • Changing board to a dataframe, since I can display it as a table in pyplot – done!


  • Here’s the code for making the chesstable table in pyplot:
    import pandas as pd
    import matplotlib.pyplot as plt
    class Chessboard():
        def __init__(self):
        def reset(self):
            self.cols = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h']
            self.rows = [8, 7, 6, 5, 4, 3, 2, 1]
            self.board = df = pd.DataFrame(columns=self.cols, index=self.rows)
            for number in self.rows:
                for letter in self.cols:
          [number, letter] = pieces.NONE.value
        def populate_board(self):
  [1, 'a'] = pieces.WHITE_ROOK.value
  [1, 'h'] = pieces.WHITE_ROOK.value
  [1, 'b'] = pieces.WHITE_KNIGHT.value
  [1, 'g'] = pieces.WHITE_KNIGHT.value
  [1, 'c'] = pieces.WHITE_BISHOP.value
  [1, 'f'] = pieces.WHITE_BISHOP.value
  [1, 'd'] = pieces.WHITE_QUEEN.value
  [1, 'e'] = pieces.WHITE_KING.value
  [8, 'a'] = pieces.BLACK_ROOK.value
  [8, 'h'] = pieces.BLACK_ROOK.value
  [8, 'b'] = pieces.BLACK_KNIGHT.value
  [8, 'g'] = pieces.BLACK_KNIGHT.value
  [8, 'c'] = pieces.BLACK_BISHOP.value
  [8, 'f'] = pieces.BLACK_BISHOP.value
  [8, 'd'] = pieces.BLACK_KING.value
  [8, 'e'] = pieces.BLACK_QUEEN.value
            for letter in self.cols:
      [2, letter] = pieces.WHITE_PAWN.value
      [7, letter] = pieces.BLACK_PAWN.value
        def print_board(self):
            fig, ax = plt.subplots()
            # hide axes
            ax.table(cellText=self.board.values, colLabels=self.cols, rowLabels=self.rows, loc='center')


  • Continuing with the MLP sequence-to-sequence NN
  • Writing
  • Reading
    • Hmm. Just realized that the input vector being defined by the query is a bit problematic. I think I need to define the input vector size and then ensure that the query creates sufficient points. Fixed. It now stores the model with the specified input vector size:


  • And here’s the loaded model in newly-retrieved data:
  • Here’s the model learning two waveforms. Went from 400×2 neurons to 3200×2:
  • Combining with GAN
    • Subtract the sin from the noisy_sin to get the moise and train on that
  • Start writing paper? What are other venues beyond GVSETS?
  • 2:00 status meeting


  • 3:30 Meeting
  • 6:00 Meeting

Phil 4.28.20


  • Upload paper to Overleaf – done!


  • Fix bug using this:
    slope, intercept, r_value, p_value, std_err = stats.linregress(xsub, ysub)
    # slope, intercept = np.polyfit(x, y, 1)
    yn = np.polyval([slope, intercept], xsub)
    steps = 0
    if slope < 0:
        steps = abs(y[-1] / slope)
    reg_x = []
    reg_y = []
    start = len(yl) - max_samples
    yval = intercept + slope * start
    for i in range(start, len(yl)-offset):
        yval += slope
  • Anything else?

GPT-2 Agents

  • Install and test GPT-2 Client
  • Failed spectacularly. It depends on a lot of TF1.x items, like There is an issue request in.
  • Checked out the project to see if anything could be done. “Fixed” the contrib library, but that just exposed other things. Uninstalled.
  • Tried using the upgrade tool described here, which did absolutely nothing, as near as I can tell


  • Continue figuring out GANs
  • Here are results using 2 latent dimensions, a matching hint, a line hint, and no hint
  • Here are results using 5 latent dimensions, a matching hint, a line hint, and no hint
  • Meeting at 10:00 with Vadim and Isaac
    • Wound up going over Isaac’s notes for Yaw Flip and learned a lot. He’s going to see if he can get the algorithm used for the maneuver. If so, we can build the control behavior around that. The goal is to minimize energy and indirectly fuel costs


Phil 4.20.20


  • Reading the Distill article on Gaussian processes (highlighted page here)
  • Copy over neural-tangents code from notebook to IDE
  • Working on regression
  • Ran into a problem with Tensorboard
    Traceback (most recent call last):
      File "d:\program files\python37\lib\", line 193, in _run_module_as_main
        "__main__", mod_spec)
      File "d:\program files\python37\lib\", line 85, in _run_code
        exec(code, run_globals)
      File "D:\Program Files\Python37\Scripts\tensorboard.exe\", line 7, in 
      File "d:\program files\python37\lib\site-packages\tensorboard\", line 75, in run_main, flags_parser=tensorboard.configure)
      File "d:\program files\python37\lib\site-packages\absl\", line 299, in run
        _run_main(main, args)
      File "d:\program files\python37\lib\site-packages\absl\", line 250, in _run_main
      File "d:\program files\python37\lib\site-packages\tensorboard\", line 289, in main
        return runner(self.flags) or 0
      File "d:\program files\python37\lib\site-packages\tensorboard\", line 305, in _run_serve_subcommand
        server = self._make_server()
      File "d:\program files\python37\lib\site-packages\tensorboard\", line 409, in _make_server
        self.flags, self.plugin_loaders, self.assets_zip_provider
      File "d:\program files\python37\lib\site-packages\tensorboard\backend\", line 183, in standard_tensorboard_wsgi
        flags, plugin_loaders, data_provider, assets_zip_provider, multiplexer
      File "d:\program files\python37\lib\site-packages\tensorboard\backend\", line 272, in TensorBoardWSGIApp
        tbplugins, flags.path_prefix, data_provider, experimental_plugins
      File "d:\program files\python37\lib\site-packages\tensorboard\backend\", line 345, in __init__
        "Duplicate plugins for name %s" % plugin.plugin_name
    ValueError: Duplicate plugins for name projector
  • After poking around a bit online with the “Duplicate plugins for name %s” % plugin.plugin_name ValueError: Duplicate plugins for name projector, I found this diagnostic, which basically asked me to reinstall everything*. That didn’t work, so I went into the Python37\Lib\site-packages and deleted by hand. Tensorboard now runs, but now I need to upgrade my cuda so that I have cudart64_101.dll
    • Installed the minimum set of items from the Nvidia Package Launcher (cuda_10.1.105_418.96_win10.exe)
    • Installed the cuDNN drivers from here:
    • The regular (e.g. MNIST) demos work byt when I try the distribution code I got this error: tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op ‘NcclAllReduce’. It turns out that there are only two viable MirroredStrategy operations, for windows, and the default is not one of them. These are the valid calls:
      distribution = tf.distribute.MirroredStrategy(cross_device_ops=tf.distribute.ReductionToOneDevice())
      distribution = tf.distribute.MirroredStrategy(cross_device_ops=tf.distribute.HierarchicalCopyAllReduce())
    • And this call is not
      # distribution = tf.distribute.MirroredStrategy(cross_device_ops=tf.distribute.NcclAllReduce()) # <-- not valid for Windows
  • Funny thing. After reinstalling and getting everything to work, I tried the diagnostic again. It seems it always says to reinstall everything
  • And Tensorboard is working! Here’s the call that puts data in the directory:
    linear_est = tf.estimator.LinearRegressor(feature_columns=feature_columns, model_dir = 'logs/boston/')
  • And when launched on the command line pointing at the same directory:
    D:\Development\Tutorials\Deep Learning with TensorFlow 2 and Keras\Chapter 3>tensorboard --logdir=.\logs\boston
    2020-04-20 11:36:42.999208: I tensorflow/stream_executor/platform/default/] Successfully opened dynamic library cudart64_101.dll
    W0420 11:36:46.005735 18544] Found more than one graph event per run, or there was a metagraph containing a graph_def, as well as one or more graph events.  Overwriting the graph with the newest event.
    W0420 11:36:46.006743 18544] Found more than one metagraph event per run. Overwriting the metagraph with the newest event.
    Serving TensorBoard on localhost; to expose to the network, use a proxy or pass --bind_all
    TensorBoard 2.1.1 at http://localhost:6006/ (Press CTRL+C to quit)
  • I got this! tensoboard
  • Of course, we’re not done yet. When attempting to use the Keras callback, I get the following error: tensorflow.python.eager.profiler.ProfilerNotRunningError: Cannot stop profiling. No profiler is running. It turns out that you have to specify the log folder like this
      • command line:
        tensorboard --logdir=.\logs
      • in code:
        logpath = '.\\logs'



  • That seems to be working! RunningTBNN
  • Finished regression chapter


  • Submitted RFI response for review


  • Got Antonio’s comments back


  • Need to work on the math to find second bumps
    • If the rate has been < x% (maybe 2.5%), calculate an offset that leaves a value of 100 for each day. When the rate jumps more than y% (e.g. 100 – 120 = 20%), freeze that number until the rate settles down again and repeat the process
    • Change the number of samples to be the last x days
  • Work with Zach to get maps up?

ML seminar

Phil 3.5.20

7:00 – 8:00-ish

  • Spent the last few days at GSAW 2020. Got to present a paper/extended abstract, and learned a lot about the ground station community. For example, I learned that The Aerospace Corporation was a Thing. Also participated in a panel on machine learning and got to tell the autonomous vehicles in a fire story. The audience paid attention! Basically, I pitched Charles Perrow a lot.
  • Started on the SDaaS white paper

Phil 2.14.20

7:00 – 8:30 ASRC GOES

This document describes the Facebook Full URL shares dataset, resulting from a collaboration between Facebook and Social Science One. It is for Social Science One grantees and describes the dataset’s scope, structure, fields, and privacy-preserving characteristics. This is the second of two planned steps in the release of this “Full URLs dataset”, which we described at

Judging Truth

    • Deceptive claims surround us, embedded in fake news, advertisements, political propaganda, and rumors. How do people know what to believe? Truth judgments reflect inferences drawn from three types of information: base rates, feelings, and consistency with information retrieved from memory. First, people exhibit a bias to accept incoming information, because most claims in our environments are true. Second, people interpret feelings, like ease of processing, as evidence of truth. And third, people can (but do not always) consider whether assertions match facts and source information stored in memory. This three-part framework predicts specific illusions (e.g., truthiness, illusory truth), offers ways to correct stubborn misconceptions, and suggests the importance of converging cues in a post-truth world, where falsehoods travel further and faster than the truth.



  •  Dissertation
    • Practice! 52 minutes, 57 seconds
    • Maybe meeting with Wayne? Nope
  • Pack, move, unpack, setup
    • Bring ethernet cables! done
    • Moved out – done
    • Moved in – not done, but ready to unpack
  • Recovered my information for GSAW and TFDev
  • Write quick proposals for:
    • cybermap – done
    • Synthetic data as a service – done
    • White paper – kinda?