Search found 97 matches

by Darklight
Wed Dec 03, 2014 4:40 pm
Forum: Applied ethics
Topic: The Expected Utility of Sex
Replies: 4
Views: 17704

Re: The Expected Utility of Sex

Good catch that the failure rate is in a given year, that was an oversight on my part. While you could probably bring the risk to an arbitrarily low amount, it will still remain non-zero, meaning that in some parallel universe the pregnancy still occurs. The heuristic moral question is really, do yo...
by Darklight
Tue Dec 02, 2014 3:06 am
Forum: Felicifia feedback and technical support
Topic: Felicifia Is No Longer Accepting New Users
Replies: 8
Views: 10088

Re: Felicifia Is No Longer Accepting New Users

Yay for being called a substantial contributor! I feel honoured, given I sometimes feel like my contributions aren't particularly substantial... XD While I do think that keeping the forums open is a good idea just in case at some point in the future the public at large becomes interested in Utilitar...
by Darklight
Tue Dec 02, 2014 3:02 am
Forum: Applied ethics
Topic: The Expected Utility of Sex
Replies: 4
Views: 17704

The Expected Utility of Sex

Long time no post. XD I've been busy with various distractions in life, and so haven't been as prolific with my silly moral theorizing lately. Nevertheless, I recently had some thoughts about the applications of Utilitarian ethics to everyday life. One particular area that I think is oft overlooked ...
by Darklight
Mon Sep 01, 2014 3:31 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Did your training set include things that were not earthquakes? If by that you mean other kinds of events, then no, the only thing I trained it on was the latitude, longitude, and magnitude of earthquakes. However, the way the training set was set up was by creating these 360 x 180 images where ear...
by Darklight
Sat Aug 30, 2014 3:59 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

I had a feeling it was something like that. Any idea why the linear model didn't do that? I'm not sure, but it seems like the linear model just overfitted or memorized the training data. The way the neural network worked, the single hidden node acted as a bottleneck that had to find some way to com...
by Darklight
Fri Aug 29, 2014 2:40 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Some bad news... upon closer inspection, it looks like my neural network earthquake predictor is broken... or rather, it cleverly just predicts the average magnitude all the time and due to the way my error calculations worked with a cutoff of magnitude 3.0 and a range of 1.0, it found a sweet spot ...
by Darklight
Thu Aug 28, 2014 8:49 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

How exactly do you measure the false positive rate? There's a huge number of earthquakes that don't happen. What I'm calling the "False Positive Rate" is simply the number of times a prediction above a certain cutoff magnitude is made where no earthquake above that magnitude actually occurs, divide...
by Darklight
Thu Aug 28, 2014 1:18 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

So, I finally got around to downloading and creating a dataset of all the recorded earthquakes from 1900 to 2014. Hopefully with this larger dataset, I can get more accurate predictions. Though most of the data from before 1973 is rather sparse, so it may not be -that- useful. On the other hand, the...
by Darklight
Tue Aug 26, 2014 6:52 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

"Earthquake Early Warning System Gave 10 Second Alert Before Napa Quake Felt" Nice! I'm in the process of putting together some code that will finally allow me to make proper future predictions. Apparently the network actually works astonishingly good on magnitudes around 4.0, but doesn't seem to p...
by Darklight
Mon Aug 25, 2014 5:50 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

I hope you're successful, so that I can tell all my friends, "Yeah, that's the guy that figured out how to predict earthquakes more accurately than anyone before. Yeah, he figured it out on the forum that I moderate. Yeah, I did my best to try and talk him out of it." ;) XD Thanks. Though I have to...
by Darklight
Mon Aug 25, 2014 3:40 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Yeah, what I had in mind is that each output is something like y = f( w * f( sum_i xi * wi ) ) , where f is sigmoid? And then if we define g = f( w * f() ), this says y = g( linear sum of inputs ), i.e., g is the link function in the generalized linear model? Of course, that's a more complicated g ...
by Darklight
Sat Aug 23, 2014 3:56 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Does that mean each output is just a function of a linear sum of the inputs? So it's as though you're doing a bunch of independent logistic regressions / generalized linear models? Each hidden node in this kind of network is roughly equivalent to a Perceptron on the input. The added output layer th...
by Darklight
Sat Aug 23, 2014 2:49 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Latest best performance results: Training Error: 89.66% Validation Error: 81.92% Test Error: 77.88% :D I made a few changes to the network to see if it would help. First, I untied the weights, as previously the weights between the hidden layer and the output layer had been tied to the weights betwee...
by Darklight
Fri Aug 22, 2014 11:03 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

It took a while, but I finally completed the closest thing to linear regression on the data. The trouble was partly due to all the memory usage, and partly because, given the official formula (normal equation) B = (XTX)^(-1)XTY, the matrix XTX (dot product of the transpose of X, and X) turned out to...
by Darklight
Thu Aug 21, 2014 5:17 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

I will probably do the toy problem at some point as you suggested. But first, the sanity check with linear regression! I was actually considering this before as well, so I figure it's worth a try. Though it appears that the way I've structured the problem, the closest equivalent to linear regression...
by Darklight
Tue Aug 19, 2014 3:09 pm
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Another update... So, by reducing the number of hidden nodes in the network to exactly one (!!!), I've managed to get the network to achieve a 92% error rate aka 8% accuracy rate on the validation set (stuff it wasn't trained on) after only three epochs (runs through the whole training set) of train...
by Darklight
Tue Aug 19, 2014 1:44 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Well, yes, I am aware that there is a large body of literature on trying to predict earthquakes using various statistical methods and that at least one paper suggests that neural networks are a promising approach, and another suggests that foreshocks are potentially useful data as precursors to eart...
by Darklight
Mon Aug 18, 2014 1:27 am
Forum: Applied ethics
Topic: Earthquake Prediction Project
Replies: 35
Views: 20562

Re: Earthquake Prediction Project

Just wanted to say that I finally got around to attempting to code this thing. My first experimental set up has consisted of taking all the earthquake data from 1973 to 2000 from the USGS website in the form of CSV files, parsing these files and creating a dataset of images that map each earthquake ...
by Darklight
Sat Jul 05, 2014 8:42 pm
Forum: Utilitarianism and friends
Topic: David Benatar, "Better Never to Have Been"
Replies: 22
Views: 15878

Re: David Benatar, "Better Never to Have Been"

I remember reading an essay by Benatar in a textbook he edited that was for a course I didn't end up taking. Apologies in advance if I get some of the following wrong, it's been a while since I read it, and I don't particularly care to read it again right now. In a word, I just disagree with Benatar...
by Darklight
Fri May 02, 2014 1:46 am
Forum: Utilitarian future
Topic: Why I Don't Prioritize GCRs
Replies: 6
Views: 5088

Re: Why I Don't Prioritize GCRs

I'm surprised that you're willing to bite the bullet on the multiplification of the value of individual lives. It becomes a principle so strong that it basically parallels the religious "sanctity of life" value. If a single death can be multiplied by a huge number then you're forced to believe that...