Monthly Archives: May 2019

Phil 5.9.19

Finished Army of None. One of the deepest, thorough analysis of human-centered AI/ML I’ve ever read.

7:00 – 4:00 ASRC NASA GOES-R

  • Create spreadsheets for tasks and bugs
  • More dissertation. Add Axelrod
  • Add reading and saving of matrices
    • Well, I can write everything, but xlsxwriter won’t read in anything
    • Tomorrow add pickling
  • Price to win analytic?

4:30 – 7:00 ML Seminar

7:00 – 9:00 Meeting with Aaron M

  • Tried to get biber working, but it produces a blank bib file. Need to look into that
  • Got the AI paper uploaded to Aaron’s new account. Arxiv also has problems with biber
  • Spent the rest of the meeting figuring out the next steps. It’s potentially something along the lines of using ML to build an explainable model for different sorts of ML systems (e.g. Humans-on-the-loop <-> Forensic, post-hoc interaction)

Phil 5.8.19

7:00 – 5:00 ASRC NASA GOES-R

  • Create spreadsheets for tasks and bugs
  • More dissertation. Add Axelrod
  • Mission Drive today, no meeting with Wayne, I think
  • Good visualization tool finds this morning:
    • Altair: Declarative Visualization in Python
    • deck.gl is a WebGL-powered framework for visual exploratory data analysis of large datasets.
  • Matrix Class
    • Change test and train within the class to input and target
    • Create the test and train as an output with the rectangular matrix with masks included. This means that I have to re-assemble that matrix from the input and target matrices
    • I still like the idea of persisting these values as excel spreadsheets
    • And now a pile of numbers that makes me happy: 
      MatrixScalar:
	rows = 5
	input_size = 5
	target_size = 5
	mask_value(hex) = -1
	tmax_cols = 6
	mat_min = 0.13042279608514273
	mat_max = 9.566827711787509

input_npmat = 
[4.384998306058251, 6.006494724381491, 7.061283542583833, 7.817876758859971, 7.214499436254831]
[0.15061642402352393, 2.818956354589415, 5.04113793598655, 6.31250083574919]
[2.8702355283795837, 5.564035171373476, 7.81403258383623, 8.590265450278785, 9.566827711787509]
[0.1359688602006689, 0.8005043254115471, 2.080391037187722, 1.9828746089685887, 2.4669996344853677]
[0.33676501126574077]

target_npmat = 
[6.529725859535821, 4.8702784287160075, 3.677355933557321, 1.5184287945320327, -0.5429800453619322]
[7.629655798004273, 8.043579124885415, 7.261429015491849, 7.137935661381686, 5.583232751491164]
[8.997538924797388, 8.32502866049641, 6.5215023090524085, 4.725363596736856, 1.3761131232325439]
[2.270623038824647, 2.430147101210101, 2.0903103552937132, 1.6846416494136842, 1.4289540998497225]
[1.897999998722116, 1.9054555934093833, 2.883358420829866, 3.703791108487346, 4.011103843736698]

scaled_input_npmat = 
[0.5608937619909073, 0.7683025595887466, 0.9032226729055693, 0.9999999999999999, 0.9228208193584869]
[0.023860024409113324, 0.44656728417761093, 0.798596002940291, 1.0]
[0.30001956916639155, 0.5815966733171017, 0.8167840813322457, 0.8979220394754807, 1.0]
[0.055115071076624986, 0.32448497933342324, 0.8432879389630332, 0.8037595876588889, 1.0]
[1.0]

scaled_target_npmat = 
[0.8352300836842569, 0.6229668973991612, 0.47037783364770835, 0.1942252150254483, -0.06945364606145459]
[1.2086581842168989, 1.2742301877146247, 1.1503252362944103, 1.1307619352630993, 0.88447239798718]
[0.9404934630223677, 0.8701974062142825, 0.6816786614665502, 0.4939321308059752, 0.143842155904721]
[0.9203986117729256, 0.9850618002693972, 0.847308741385268, 0.6828706522143898, 0.5792275279958895]
[5.635977418165948, 5.658116281877606, 8.561929904750741, 10.998147030080538, 11.910690569251393]

scaled, masked input = 
[[ 0.56089376  0.76830256  0.90322267  1.          0.92282082]
 [-1.          0.02386002  0.44656728  0.798596    1.        ]
 [ 0.30001957  0.58159667  0.81678408  0.89792204  1.        ]
 [ 0.05511507  0.32448498  0.84328794  0.80375959  1.        ]
 [-1.         -1.         -1.         -1.          1.        ]]
scaled target = 
[0.8352300836842569, 0.6229668973991612, 0.47037783364770835, 0.1942252150254483, -0.06945364606145459]
[1.2086581842168989, 1.2742301877146247, 1.1503252362944103, 1.1307619352630993, 0.88447239798718]
[0.9404934630223677, 0.8701974062142825, 0.6816786614665502, 0.4939321308059752, 0.143842155904721]
[0.9203986117729256, 0.9850618002693972, 0.847308741385268, 0.6828706522143898, 0.5792275279958895]
[5.635977418165948, 5.658116281877606, 8.561929904750741, 10.998147030080538, 11.910690569251393]

scaled = [ 6.52972586  4.87027843  3.67735593  1.51842879 -0.54298005], error = 0.0
scaled = [7.6296558  8.04357912 7.26142902 7.13793566 5.58323275], error = 0.0
scaled = [8.99753892 8.32502866 6.52150231 4.7253636  1.37611312], error = 0.0
scaled = [2.27062304 2.4301471  2.09031036 1.68464165 1.4289541 ], error = 0.0
scaled = [1.898      1.90545559 2.88335842 3.70379111 4.01110384], error = 0.0

input_train = 
[[ 0.05511507  0.32448498  0.84328794  0.80375959  1.        ]
 [-1.         -1.         -1.         -1.          1.        ]
 [ 0.30001957  0.58159667  0.81678408  0.89792204  1.        ]]

input_test = 
[[ 0.56089376  0.76830256  0.90322267  1.          0.92282082]
 [-1.          0.02386002  0.44656728  0.798596    1.        ]]

target_train = 
[[ 0.92039861  0.9850618   0.84730874  0.68287065  0.57922753]
 [ 5.63597742  5.65811628  8.5619299  10.99814703 11.91069057]
 [ 0.94049346  0.87019741  0.68167866  0.49393213  0.14384216]]

target_test = 
[[ 0.83523008  0.6229669   0.47037783  0.19422522 -0.06945365]
 [ 1.20865818  1.27423019  1.15032524  1.13076194  0.8844724 ]]

       

Phil 5.7.19

7:00 – 8:00 ASRC NASA GOES-R

  • Via CSAIL: “The team’s approach isn’t particularly efficient now – they must train and “prune” the full network several times before finding the successful subnetwork. However, MIT professor Michael Carbin says that his team’s findings suggest that, if we can determine precisely which part of the original network is relevant to the final prediction, scientists might one day be able to skip this expensive process altogether. Such a revelation has the potential to save hours of work and make it easier for meaningful models to be created by individual programmers and not just huge tech companies.”
    • From the abstract of The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
      : We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the “lottery ticket hypothesis:” dense, randomly-initialized, feed-forward networks contain subnetworks (“winning tickets”) that – when trained in isolation – reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective. 
    • Sounds like a good opportunity for evolutionary systems
  • Finished with text mods for IEEE letter
  • Added Kaufman and Olfati-Sabir to the discussion on Social Influence Horizon
  • Started the draft deck for the tech summit
  • More MatrixScalar
    • Core functions work
    • Change test and train within the class to input and target
    • Create a coordinating class that loads and creates test and train matrices
  • JuryRoom meeting
    • Progress is good enough to start tracking it. Going to create a set of Google sheets that keep track of tasks and bugs

Phil 5.6.19

7:00 – 5:00 ASRC GOES-R

  • Finished the AI/ML paper with Aaron M over the weekend. I need to have him ping me when it goes in. I think it turned out pretty well, even when cut down to 7 pages (with references!! Why, IEEE, why?)
    • Sent a copy to Wayne, and distributed around work. Need to put in on ArXiv on Thursday
  • Starting to pull parts from phifel.com to make the lit review for the dissertation. Those reviews may have had a reason after all!
    • And oddly (though satisfying), I wound up adding a section on Moby-Dick as a way of setting up the rest of the lit review
  • More Matrix scalar class. Basically a satisfying day of just writing code.
  • Need to fix IEEE letter and take a self-portrait. Need to charge up the good camera

Phil 5.3.19

8:00 – 5:00 ASRC AIMES

  • I may need to do something Star Wars-ish tomorrow
  • Didn’t get the Google AI for Social Good. Sigh
  • Working on the MatrixScalar class
    • use np.array as core type?
    • Good progress. I can build a scaled, square matrix
    • Need to add a log(x)/10X scale/rescale

Phil 5.2.19

7:00 – 9:00 ASRC NASA

  • Wrote up my notes from yesterday
  • Need to make an Akido Drone image, maybe even a sim in Zach’s environment?
  • Changed the title of the Dissertation
  • Need to commit the changes to LMN from the laptop – done
  • Need to create an instance of the JASSS paper in overleaf and make sure it runs
  • Put the jasss.bst file in the svn repo – done
  • Thinking about putting my dict find on stackoverflow, but did see this page on xpath for dict that is making me wonder if I just shouldn’t point there.
  • Did meaningless 2019 goal stuff
  • Adding ragged edge argument and generate a set of curves for eval
  • ML seminar 4:30
  • Meeting with Aaron M at 7:00
    • Spent a good deal of time discussing the structure of the paper and the arguments. Aaron wants the point made that the “arc to full autonomy” is really only the beginning, predictable part of the process. In this part, the humans own the “reflective part” of the process, either as a human in the loop, where they decide to pull the trigger, or in the full autonomy mode where they select the training data and evaluation criteria for the reflexive system that’s built. The next part of that sequence is when machines begin to develop reflective capabilities. When that happens, many of the common assumptions that sets of human adversaries make about conflict (OODA, for example), may well be disrupted by systems that do not share the common background and culture, but have been directed to perform the same mission.

Phil 5.1.19

7:00 – 7:00 ASRC NASA AIMS

  • Added lit review section to the dissertation, and put the seven steps of sectarianism in.
  • Spent most of yesterday helping Aaron with TimeSeriesML. Currently working on a JSON util that will get a value on a provided path
  • Had to set up python at the module and not project level, which was odd. Here’s how: www.jetbrains.com/help/idea/2016.1/configuring-global-project-and-module-sdks.html#module_sdk
  • Done! 
        def lfind(self, query_list:List, target_list:List, targ_str:str = "???"):
        for tval in target_list:
            if isinstance(tval, dict):
                return self.dfind(query_list[0], tval, targ_str)
            elif tval == query_list[0]:
                return tval

    def dfind(self, query_dict:Dict, target_dict:Dict, targ_str:str = "???"):
        for key, qval in query_dict.items():
            # print("key = {}, qval = {}".format(key, qval))
            tval = target_dict[key]
            if isinstance(qval, dict):
                return self.dfind(qval, tval, targ_str)
            elif isinstance(qval, list):
                return self.lfind(qval, tval, targ_str)
            else:
                if qval == targ_str:
                    return tval
                if qval != tval:
                    return None

    def find(self, query_dict:Dict):
        # pprint.pprint(query_dict)
        result = self.dfind(query_dict, self.json_dict)
        return result
  • It’s called like this: 
    ju = JsonUtils("../../data/output_data/lstm_structure.json")
# ju.pprint()
result = ju.find({"config":[{"class_name":"Masking", "config":{"batch_input_shape": "???"}}]})
print("result 1 = {}".format(result))
result = ju.find({"config":[{"class_name":"Masking", "config":{"mask_value": "???"}}]})
print("result 2 = {}".format(result))
  • Here’s the results: 
    result 1 = [None, 12, 1]
result 2 = 666.0
  • Got Aaron’s code running!
  • Meeting with Joel
    • A quicker demo that I was expecting, though I was able to walk through how to create and use Corpus Manager and LMN. Also, we got a bug where the column index for the eigenvector didn’t exist. Fixed that in JavaUtils.math.Labeled2DMatrix.java
  • Meeting with Wayne
    • Walked through the JASSS paper. Need to make sure that the lit review is connected and in the proper order
    • Changed the title of the dissertation to
      • Stampede Theory: Mapping Dangerous Misinformation at Scale
    • Solidifying defense over the winter break, with diploma in the Spring
    • Mentioned the “aikido with drones” concept. Need to make an image. Actually, I wonder if there is a way for that model to be used for actually getting a grant to explore weaponized AI in a way that isn’t directly mappable to weapons systems, but is close enough to reality that people will get the point.
    • Also discussed the concept of managing runaway AI with the Sanhedrin-17a concept, where unanimous agreement to convict means acquittal.  Cities had Sanhedrin of 23 Judges and the Great Sanhedrin had 71 Judges en.wikipedia.org/wiki/Sanhedrin
      • Rav Kahana says: In a Sanhedrin where all the judges saw fit to convict the defendant in a case of capital law, they acquit him. The Gemara asks: What is the reasoning for this halakha? It is since it is learned as a tradition that suspension of the trial overnight is necessary in order to create a possibility of acquittal. The halakha is that they may not issue the guilty verdict on the same day the evidence was heard, as perhaps over the course of the night one of the judges will think of a reason to acquit the defendant. And as those judges all saw fit to convict him they will not see any further possibility to acquit him, because there will not be anyone arguing for such a verdict. Consequently, he cannot be convicted.