A.I. Experiments: Visualizing High-Dimensional Space
About | Information | History | Online | Facts | Discovery
Check out https://g.co/aiexperiments to learn more. This experiment helps visualize what’s happening in machine learning. It allows coders to see and explore their high-dimensional data. The goal is to eventually make this an open-source tool within TensorFlow, so that any coder can use these visualization techniques to explore their data. http://g.co/aiexperiments Built by Daniel Smilkov, Fernanda Viégas, Martin Wattenberg, and the Big Picture team at Google. More resources: http://www.tensorflow.org
Comments
-
this is a great explanation! although i do have a quick question, so if we treat a pixel as a dimension doesnt that limit the usage of this technique to simple images? since a more complex image would have many more pixels and thus the dimensions would be massive, wouldn't this hinder the processing time and cluster formation, aka it would take forever for it to form clusters, just a question, if anyone with more experience with ML can chime that would be awesome!
-
How much space does it take up? if it learns that fast then it needs alot of memory to store all that data
-
Skynet is near!
-
Não tem como não reconhecer esse sotaque. Kkkkkkkk
-
Hmm interesting Google and thank you for sharing.
-
I bet it can't read my bad handwriting
-
This is so. cool. °v° Thank you for making all of this stuff publicly available!
-
Hey, can you just hang on with this thing? I translate documents for a living and this is pretty scary. Please stop it, Google!
-
SkyNet is coming soon, pals...
-
Nice explanation. It all makes sense why you built a tensor accelerating unit now.
-
what should i be learning/praticing before i can tackle tensorflow ?
-
Hacked Roblox servers...
-
i wonder, could you use T-SNE to partially decode the Voiniech manuscript?
-
I uderstand that it is still being developed and not available for use, right? If so, when it would be possible to try out?
-
add probability of occurrence == multi dimensional filter ...then get fast high probability of understanding whats going on with just few infopoints just like our brain works
-
how i can try it?
-
Nice, that was a very helpful explanation. I feel like I understand machine learning a bit better now.
-
...This is amazing. It's amazing because the tool can exhibit words that are worth learning and related words. This can be insanely helpful when learning important terms for some field in particular. I can't wait to get my hands on this.
-
Which software are you using? I downloaded t-sne for python but ended up with a tkinter plot.. How to get that interactive plot?
3m 17sLenght
803Rating