|
flakeloaf posted:i miss markov polov wait what happened to it did it become racist and get banned
|
# ? May 30, 2019 18:42 |
|
|
# ? May 11, 2024 16:15 |
|
thanks for ml learning advice
|
# ? May 30, 2019 19:21 |
|
N-N-N-NINE BREAKER posted:wait what happened to it *makes jerking off motion* eventually!
|
# ? May 30, 2019 19:38 |
|
DONT THREAD ON ME posted:has anyone developed an ML algorithm that can tell you if the thing you're about to post is problematic? i was thinking the other day that ML algorithms would actually be fantastic for identifying biases in a process, if anyone bothered to use them that way
|
# ? May 30, 2019 20:17 |
|
The Management posted:it’s a loving filter. all programs are filters.
|
# ? May 30, 2019 20:28 |
|
rotor posted:all programs are filters. so i guess that makes AI the great filter?
|
# ? May 30, 2019 20:35 |
|
ai won't kill us, but it should because we deserve it
|
# ? May 30, 2019 20:38 |
|
animist posted:ai won't kill us not all of us anyway, and certainly not all at once.
|
# ? May 30, 2019 20:42 |
|
honestly i think trumps brain is just a machine learning matrix for owning liberals
|
# ? May 30, 2019 20:44 |
|
reverse the direction so instead of reducing dimensionality, it increases, like https://science.sciencemag.org/content/358/6364/793 (like the second half of a autoencoder)
|
# ? May 30, 2019 20:47 |
|
Lysidas posted:reverse the direction so instead of reducing dimensionality, it increases, like https://science.sciencemag.org/content/358/6364/793 i wanna make a robot nose that u put in ur house and uses ml to detect different smells like carbon monoxide or formaldehyde or various vocs or who just farted. and every once in a while, the model gets updated and sent to all noses so now it can know new smells. two problems tho are: 1. if they dont match spec exactly (like down to the size of each hair sensor) then theyll each need to be retrained every time a new model gets pushed. u might be able to build that training data in factory, but itll still be super annoying 2. theyll probs get clogged, so youll need it to be able to sneeze once a week to clear itself out
|
# ? May 30, 2019 21:34 |
|
this system discriminates against people who clean themselves regularly
|
# ? May 30, 2019 21:45 |
|
oh yeah i just remembered that google was offering free gpu and tpu compute https://cloud.google.com/tpu/docs/colabs https://www.easterscience.com/google-is-offering-free-tpu-and-gpu-for-ai-using-colaboratory-colab/ now you can work on your (pattern matcher/filter/fancy stats/the other 96 names of machine learning) project without having it cut into your regular 4k hd 3d vr porn time because you had to use those sweet sweet twin gtx 2080ti's you bought that you were totes gonna use to make an ai chattebotte
|
# ? May 30, 2019 23:13 |
|
google along with a lot of other actors have realized that a lot of successful ml simply involves ridiculous amounts of semi-skilled man-hours tweaking parameters and topologies randomly until the thing seems to do the thing, so it is worth it to try to capture more hands early on. there's some glimmers of theoretical work happening on what works and what doesn't, notably lin-tegmark(-rolnick) https://arxiv.org/abs/1608.08225v4 , which does the very basic needful demonstrating that e.g. encoding multiplication requires exponentially wide hidden layers, which should reasonably be interpreted as "cannot be learned with current methods". i never find the time, but i am personally quite sure that it is a pretty doable task to draw from minsky's perceptrons book (which famously killed off neural networks last time they were popular) the needed machinery, combined with reasonable assumptions on what is the limits of learning (e.g. finite precision) to demonstrate that some practical-sounding problems cannot be taught to deep neural networks without encoding as much information as a full table realization of the function requires. which should again be interpreted as "cannot be learned with current methods". i don't think such a paper would change the enthusiasm that much, but it is one of those directions that ought to be investigated sooner or later.
|
# ? May 31, 2019 10:29 |
|
to do ml you need lots of data. there are a few types of data: * open source standard image recognition etc data sets. only use this if you are confident your technique is better than the previous attempts. * random free data you can find to download on the internet. this is normally boring stuff like poverty rates in different postal areas or how polluted a river is at different points along its course. skip this stuff unless you're doing a thesis for uni * "free" data which isn't sold as such, but you can scrape from the web. this might how much a phone charger costs on amazon. more interesting but you will need to have some proxies and some dev time to get the data. the cheapest proxies are bot nets or these guys who totally have their endpoints consent https://luminati.io/ * financial data vendors will happily sell you lots of data for lots of money, but everything about the experience will suck. they will all handle edge cases in different ways. there will be bullshit restrictions on how you can use the data (only on one machine, can't make a graph and show it to a client etc) but you can ignore those * the good stuff is the personal behaviour data. this is geolocation (from phones), internet searches and traffic (from free "antivirus"), emails (from email apps and spam removers), credit card transactions (idk exactly how they get this i think it's apps as well). this stuff is all expensive and the vendors are rubbish at delivery. occaisionally they'll gently caress up and send you some non-anonymised data (as though you couldn't work out who spent 8 hours at a school and then 3 at a strip club was if you really wanted to) at which point they'll email you and tell you to delete it and import a new version. might be tricky to get some of this past your ethics committee at uni but it's all legal, even in the EU as it is anonymised. for supervised learning you'll need a training set. outsource this to india for best results. distortion park fucked around with this message at 14:43 on May 31, 2019 |
# ? May 31, 2019 14:35 |
|
pointsofdata posted:(as though you couldn't work out who spent 8 hours at a school and then 3 at a strip club was if you really wanted to) Look, she’s working her way though Medical School, ok?
|
# ? May 31, 2019 14:41 |
|
animist posted:okay, so, first thing you gotta understand is what people mean by "deep neural networks". a neural network is made up of "neurons", which are functions of weighted sums. thats it. here's a "neuron": hey now posting convnets is cheating
|
# ? May 31, 2019 19:07 |
|
also i feel bad for recognizing some of those from illustrations alone
|
# ? May 31, 2019 19:14 |
|
lancemantis posted:also i feel bad for recognizing some of those from illustrations alone seek help
|
# ? May 31, 2019 21:16 |
|
it's my world now fortunately/unfortunately
|
# ? May 31, 2019 21:17 |
|
For real though anyone doing research in ML or machine vision should stop. The downsides of these technologies significantly outweigh the benefits.
|
# ? Jun 1, 2019 01:06 |
|
tbh that can be said of pretty much any technology
|
# ? Jun 1, 2019 04:52 |
|
it's been all downhill since the stick with a rock on the end imo
|
# ? Jun 1, 2019 05:02 |
|
Cybernetic Vermin posted:google along with a lot of other actors have realized that a lot of successful ml simply involves ridiculous amounts of semi-skilled man-hours tweaking parameters and topologies randomly until the thing seems to do the thing, so it is worth it to try to capture more hands early on. I’m not an academic type but if I’m reading this correctly you’re saying that ML is horseshit, and I can confirm this from practical experience.
|
# ? Jun 1, 2019 06:21 |
|
lancemantis posted:tbh that can be said of pretty much any technology you can say anything you can think of but for some things its true and for some things its not
|
# ? Jun 1, 2019 06:56 |
|
neural networks (ML) aren’t entirely horseshit, it’s just that what they actually let you do is far less than what a bunch of idiots eager for your cash let you do animals do use neural nets for “everything,” sure, but real neurons are a bit more than simple integrators, so we’re not really very close to actually using neural nets the way animals do and getting the benefits of a faster substrate instead we’re able to do basically one simple task in a way we don’t really understand, and we push even that far beyond reasonable use if I were asked to make an “object recognizer,” I wouldn’t train one huge network on a million images of the object I want to recognize and allow steganography to break everything, I’d train a large number of smaller networks on different characteristics to recognize, and use additional separate networks to determine confidence according to recognitions, etc. finally arriving at the one confidence value
|
# ? Jun 1, 2019 07:15 |
|
eschaton posted:if I were asked to make an “object recognizer,” I wouldn’t train one huge network on a million images of the object I want to recognize and allow steganography to break everything, I’d train a large number of smaller networks on different characteristics to recognize, and use additional separate networks to determine confidence according to recognitions, etc. finally arriving at the one confidence value This is actually basically Fast R-CNN - except object classification was done by SVMs instead of NNs really all the convnet did for that is feature encoding it’s called fast rcnn but it’s pretty slow compared to the approaches that supplanted it
|
# ? Jun 1, 2019 13:53 |
|
eschaton posted:if I were asked to make an “object recognizer,” I wouldn’t train one huge network on a million images of the object I want to recognize and allow steganography to break everything, I’d train a large number of smaller networks on different characteristics to recognize, and use additional separate networks to determine confidence according to recognitions, etc. finally arriving at the one confidence value “What if the three blind men and the elephant only it were a good thing?”
|
# ? Jun 1, 2019 13:56 |
|
oh and also fast rcnn was doing that all given that you were already giving it proposals for where objects in the image were
|
# ? Jun 1, 2019 13:57 |
|
eschaton posted:I’d train a large number of smaller networks on different characteristics to recognize, and use additional separate networks to determine confidence according to recognitions, etc. finally arriving at the one confidence value Thats what resnet does, except it picks those attributes automatically and you can later verify what each output from each layer means. And what u can also do is load resnet and train the last layers with new images to detect the things u want (like different breeds of animals). Then u dont need millions of images anymore. You can get by with like 30 and it will still be super accurate for ur new specific case.
|
# ? Jun 1, 2019 14:20 |
|
One of the most valuable parts of ml is u can take a existing model and then train it with ur data to make it do what u want. So with each new tech, u wait for the super nerds to do all the work for u, then u use their model to do ur stuff easy peasy.
|
# ? Jun 1, 2019 14:22 |
|
well resnet is more of a particular convnet architecture, like the densenet illustration at the end of that earlier post, than a particular machine vision objective
|
# ? Jun 1, 2019 14:53 |
|
like pre-convnet image classification and object detection (which are overlapping tasks really) was all about using something like sift vectors, which was pretty much taking an image and encoding it into this vector where each dimension represented some particular human chosen function output and you hoped that the vectors were distinct enough that images of different things would encode distinctly but that also the encoding was general/robust enough that changes in pose or scale/distance wouldn’t prevent things from matching up so an objective like object detection was a bunch of sliding various windows of subsections of the image and searching your database of sift vectors to see if anything matched and of course there was research into how to partition and search through that database of sift vectors faster etc
|
# ? Jun 1, 2019 15:05 |
|
don't ask me about deploying mask r-cnn models to production systems with no quantifiable validation metrics or model versioning
|
# ? Jun 1, 2019 15:26 |
|
rchon posted:don't ask me about deploying mask r-cnn models to production systems with no quantifiable validation metrics or model versioning bonus if it’s just the Facebook repo
|
# ? Jun 1, 2019 15:42 |
|
lancemantis posted:bonus if it’s just the Facebook repo matterport, actually (detectron apparently doesn't run in a vm with cpu and 2gb of ram. still want to try maskrcnn-benchmark though because it's in pytorch.)
|
# ? Jun 1, 2019 16:08 |
|
lancemantis posted:hey now posting convnets is cheating ill have you know that convnets are an extremely exciting area of research with wide-reaching implications in the fields of speech synthesis and niche pornography
|
# ? Jun 1, 2019 20:43 |
|
is attention just more matrices multiplied together and trained the standard way should i be blindly copying code i don't understand from random transformer repositories instead of from rnn tutorials
|
# ? Jun 1, 2019 21:02 |
|
suffix posted:should i be blindly copying code i don't understand from random repositories I mean you’re doing machine learning aren’t you?
|
# ? Jun 1, 2019 21:09 |
|
|
# ? May 11, 2024 16:15 |
|
interpretabilityposting: how tf do you understand what's going on in a deep convnet? how do you know what the network will do? some people have tried using like, formal proofs and geometry to describe network behavior. sometimes they can get this to work for more than, like, 10 neurons. but it's mostly useless for larger networks. too many variables, too high-dimensional. more interesting approaches for understanding neural networks are empirical, imo: do experiments, treat neural networks like lab animals and try to do biology to them. the best recent paper is prolly https://distill.pub/2018/building-blocks/ which is fun to play around with in the browser if you've got 10 minutes. their code hallucinates images that activate different slices of a neural network; you can tell it to activate some neuron or group of neurons and it'll make a picture that activates them. sometimes the pictures even make sense. it's hard to tell what extent that's just pareidolia and selection bias, though. if you reimplement that paper but don't tune your hallucination code right, you'll just get white noise instead of pictures of dogs for your visualizations; and there's no reason to assume that white noise is a worse description of the behavior of the network than the dog pictures. it's like... trying to understand how a squid thinks by FMRIing its brain. but then only using the FMRIs that you think look cool. idk. the other super cool empirical paper to come out recently is the lottery ticket hypothesis, which has pretty far-reaching implications if it turns out to be true. it's suggesting that the big convnets we're training are actually tools that let us do searches over combinatorially-huge numbers of smaller meaningful subnetworks. basically if you throw a giant bucket of spaghetti at the wall a little bit of the spaghetti will stick. if it pans out it could explains why, like, deep learning works at all. on the other hand it might be bupkis
|
# ? Jun 1, 2019 21:13 |