I agree in sentiment and can't find the link now but just yesterday I read an article saying the doj or fbi or someone like that had stated that just using Monero or zcash is suspicious behavior. I think this is part of changing the narrative from cryptocurrencies are bad to these ones are good (btc, eth,...) and anyone who uses any other ones is therefore definitely bad
I know the answer is to just write what I'm describing myself but does anyone know of an existing way to find the best SciKitLearn algorithm for a particular problem. Like if I want to find the regression fit is there a way to just pass in the data and have it trained,tested on all of the regression algorithms in SKLearn? My current workflow is to just pick a handful of algorithms that sound like they should be good for the problem at hand and try each one of them manually. Igel seems like a step towards making this sort of thing possible if another tool doesn't exist already.
Hi, we should be careful with the feature you are talking about. The results from all machine learning algorithm can be very misleading and probably some models will overfit the data.
So, if you throw some data and fit all machine learning models on it and then compare the performance. You will probably receive misleading values since different models require different tuning approaches. It's not as easy as you said it, you can't just feed data (also depends on the data) to models and expect to get the best model at the output.
One approach I can think of here is to integrate cross validation and hyperparameter tuning with your suggestion. However, I can imagine that this can be computationally expensive. I will take it into consideration as an enhancement for the tool. Thanks for your feedback
Thank you for explaining this more indepth. I should have been more specific with my original comment, I did intend cross validation and hyper parameter tuning as inclusing to the automatic feature I was describing.
These operations certainly are computationally expensive, a recent hyperparameter tuning operation locked up my laptop for 3 days but this seems to be the case for any similar operation. The only approaches I've come across so far to overcome it are things like converting the data to smaller sizes (which seems outside the scope of this tool) and some way to batch the data so that it can be "paused" and resumed as needed. Thank you again for creating Igel.
Hey, I really appreciate your answer to this question. As I was reading the question, red flags started popping up in my mind about the risk of overfitting when using the ensemble approach, and I think your response was spot on for how an ML researcher would go about it! Most ML professionals I've talked to have been really against making a user friendly ML suite because of how easy it is to misuse these algorithms.
Triage is built for this: training and evaluating giant grids of models & hyperparameters using cross-validation. Similar to igel, it abstracts ML to config files and a CLI.
It's designed for use in a public policy context, so it works best with:
- binary classification problems (ex: the evaluation module is designed for binary classification metrics)
- problems that have a temporal component (the cross validation system makes some assumptions about this)
I stand by my view that anyone should have right to kill themselves.
I would be very sad if someone close to me did so but that shouldn't stop them from doing it. I consider this a basic freedom of being a living creature. If you don't have the power to end your life then do you really own it?
It's pretty much impossible to take away that freedom, killing yourself is not particularly difficult. The more interesting question is whether someone else should be able to kill you, if they think it is what you want.
And I think suicide prevention is still very important, since many people who attempt to commit suicide regret it afterwards.
The problem isn't ending one's own life, but doing so with dignity, in an orderly fashion. How not to leave a mess behind? That takes solid preparation, which is difficult given the massive social stigma. Wouldn't it be nice if one didn't need an "excuse", like a terrible disease, to be allowed an uneventful exit? I'd find it a liberating idea if such a thing were normalized. Parties are more enjoyable when you can leave any time you like. Let me stay just because I want to, without worries what will happen should I change my mind.
At the end my dad asked the nurses to stop the oxygen he got via a mask. They called a doctor who made sure he knew what the likely consequences of his request would be, and he assured the doctor he did. So they turned it off and took of his mask. He passed away a few hours later.
Technically I guess this is assisted suicide. He had untreatable cancer in the lungs, he'd just gotten pneumonia and he and the doctor knew it wasn't going to get better. So he decided his time was up.
But from what I understand this is not the common case. Rather it is people who struggle with their emotions[1][2], which can pass or be treated. For those I think it's important to not give in to their temporary wishes, and to help them get past it.
I find it pretty crazy that suicide is considered bad, it's kind of selfish honestly. Of course there's a lot of situations in which the way the person feels is just temporary, but a lot of suicides aren't a spur of the moment decision. People often think about such an important decision very carefully.
The lengths psychiatric institutions and society is willing to go in order to deny you the choice of living is absolutely disgusting.
Most people consider other people who want to kill themselves in a point in time as having temporary insanity so stopping them in the act is ok, because it is not 'them'.
It is also ok to want to stop people wanting to long term kill themselves like stopping adictive behavior.
Using force here might be controversial but we can just do the same playbook as addiction.
Highly recommend you keep going with it when time allows. I got my wEMT license a few years back and although it's lapsed now it was a really fun and educating experience. For those who don't have one near them I recommend SOLO school in new england -> https://soloschools.com/
I think this sounds like the right idea to move towards. With so many similarities in their offerings it seems like the logical next step. Maybe a company can be created to offer a middleware that abstracts all the common offerings into your spec because I don't expect the major cloud providers to do that on their own soon. Cheers to your upcoming IPO when this works out
I think this looks great, I definitely will want to use it. I tried to read some of the popular posts and found a small bug:
When you are on a post page (like https://vigyaa.io/sadness-is-confusing-86b8c139/) it loads the content of the page and you can scroll and everything but then after a few seconds it switches to "Something Went Wrong!!! Please Try again".
Watching it happen with the console open this error comes out when it fails:
TypeError: NetworkError when attempting to fetch resource.
+1 this could easily be the story line of a Rick and Morty episode or any of the other similar off the cuff shows that are popular right now. I think that will be one of the main profit streams for things like this, you can get the weird wild stories that don't really make sense but are interesting enough that who cares and you don't have to associate your network with eccentric individuals that attract malcontents.
Thank you for making this it's cool and is basically the exact way that I use Keynotes on Mac to organize ideas (only better because of adding videos and other content)
