bluemellophone

@bluemellophone@lemmy.world

• ⁨Comment⁩ on ⁨Can you think of any now?⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  No, you are correct. Hinton began researching ReLUs in 2010 and his students Alex Krizhevsky and Ilya Sutskever used it to train a much deeper network (AlexNet) to win the 2012 ILSVRC. The reason AlexNet was so groundbreaking was because it brought all of the gradient optimization improvements (SGD with momentum as popularized by Schmidhuber, and dropout), better activation functions (ReLU), a deeper network (8 layers), supervised training on very large datasets (necessary to learn good general-purpose convolutional kernels), and GPU acceleration into a single approach.

  NNs, and specifically CNNs, won out because they were able to create more expressive and superior image feature representations over the hand-crafted features of competing algorithms. The proof was in the vastly better performance, it was a major jump when the ILSVRC was becoming saturated. Nobody was making nearly +10% improvements on that challenge back the , it blew everybody out of the water and made NNs and deep learning impossible to ignore.

• ⁨Comment⁩ on ⁨Can you think of any now?⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  Before LeNet and AlexNet, SVMs were the best algorithms around. People used HOG+SVM, SIFT, SURF, ORB, older Haar / Viola-Jones features, template matching, random forests, Hough Transforms, sliding windows, deformable parts models… so many techniques that were made obsolete once the first deep networks became viable.

  The problem is your schooling was correct at the time, but the march of research progress eventually saw 1) the creation of large, million-scale supervised datasets (ImageNet) and 2) larger / faster GPUs with more on-card memory.

• ⁨Comment⁩ on ⁨Murica⁩ ⁨⁨7⁩ ⁨months⁩ ago⁩:

  I was speaking anecdotally, but it’s good to back that up with some data.

  …copernicus.org/…/egusphere-2023-176.pdf

  Page 15, Table 1 shows a clean table, with Denmark in the bottom 10 for large hail size in European countries; relative to places like Germany, large hail (the kinds you’d really want to avoid while on a bike) in Denmark is considerably more rare. That study only has two citations, though, so not the greatest source.

  This survey is much better cited and comments on hail throughout Europe and in Denmark, but I can’t access the PDF at the moment: www.sciencedirect.com/…/S0169809516300291

• ⁨Comment⁩ on ⁨Murica⁩ ⁨⁨7⁩ ⁨months⁩ ago⁩:

  I never said they don’t get hail, I said they don’t get regular hail. In general, hail is uncommon in Denmark, and large hail is even more rare.

• ⁨Comment⁩ on ⁨Murica⁩ ⁨⁨7⁩ ⁨months⁩ ago⁩:

  Yeah… pretty sure Denmark doesn’t get regular weekly thunderstorms or hail storms.

• ⁨Comment⁩ on ⁨Murica⁩ ⁨⁨7⁩ ⁨months⁩ ago⁩:

  Taking a vacation road trip from Florida to the Grand Canyon with three kids with only bikes also comes at quite the cost. Bikes are great, but in many practical scenarios they are slow. Not all of us live in Manhattan, or a dense city, or even a well connected and safe to traverse suburb.

  The cost is time.

• ⁨Comment⁩ on ⁨Oxygen⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  For those who haven’t read it:

  Jazz hands, bitches!

  That’s all you get.

• ⁨Comment⁩ on ⁨Oxygen⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Everybody in this thread needs to read Project Hail Mary by Andy Weir.

• ⁨Comment⁩ on ⁨Butts⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Exactly how would carbon dioxide get exchanged if the lungs are damaged?

• ⁨Comment⁩ on ⁨Slapping Chicken⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  It’ll 100% be chickcoal since the hand will be pushing Mach 5. Pretty sure the plasma will give it a nice sear.

• ⁨Comment⁩ on ⁨Predator Vision⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Why stop there, here is a much better picture for primal fear response: www.nbcnews.com/id/wbna27426933

• ⁨Comment⁩ on ⁨Think about it⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  I’ll bring hammocks

• ⁨Comment⁩ on ⁨8 Minutes⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  It takes 8 minutes for the light to travel from the sun to Earth. Because light in a vacuum travels faster than anything, including information, we would not and could not know it had disappeared for 8 minutes. This means Earth would continue to follow its orbit around a non-existent sun for 8 minutes because the Sun’s gravity would still be acting on the Earth.

  If it was nighttime, you wouldn’t notice the sudden lack of sunlight (other than if it was a full moon) but you’d almost certainly notice the change in gravity.

• ⁨Comment⁩ on ⁨“A simple calculation”⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Reinforcement learning is a machine learning (ML) technique (“AI” in layman terms) for optimizing neural networks and other types of non-linear models.

  As far as ML math goes, this is fairly tame. It looks complicated, but is spelled out clearly in the paper. A lot of these kind of theoretical papers — things that would get published in Automatica — are going to lean very heavy on math.

  Source: PhD in Computer Science with dissertation using neural networks.

• ⁨Comment⁩ on ⁨Academia to Industry⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  It’s a lot of fucking work. If you enjoy hard work, learning about the latest advancements in your field, and can handle disappointment / criticism well, then it’s something to look into.

• ⁨Comment⁩ on ⁨Burrito⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Who’s to say this isn’t for animal health research?

• ⁨Comment⁩ on ⁨Meet my new puppy: Ass!⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Tums

• ⁨Comment⁩ on ⁨You can't see him!!!!⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  If this is real, anybody got an arxiv link?