would be nice to have an option to increase the size of the preview images.
2 Likes
@jeremy invited us to think about how this might be used for text analysis.
In image recognition we are scanning pixels, ie data at a low level, to allow the computer to classify things that are high-level. This classification, though it is done by means that may or may not mirror what we actually do, arrives at a human-recognizable result. And it does this with the aim of hitting a target label, ie it’s supervised learning.
If we use this for language, the data-at-a-low-level piece is sometimes words (although some words are less atomic than others). Words when assembled into phrases and sentences create something higher-level and human-recognizable – ideas, or concepts, or really ‘the thing that’s being passed between us when we communicate’.
So one task would be to train the model with a limited number of human-defined labels for whatever is being communicated. I did some of this for a passage from Harry Potter 
. It isn’t all that difficult. What is an interesting challenge is that it’s difficult to do on just one level, just one time through. For instance ‘He had stayed still a second too long.’ So first there’s the idea of the sentence: something bad had happened because he’d stayed in one place without moving.
Then there’s He (which is pretty atomic) then ‘had stayed’ which is back in time before something else just happened, combined with not physically moving. Then ‘a second too long’, which could also be further broken down on another pass. Yes, you could do ‘a’ and ‘second’ and ‘too’ and ‘long’ but you could also describe it in terms that are closer to what we’re getting when it’s passed from J.K. Rowling’s brain into ours. Something like time, a small unit of time, an allowed length of time, and that allowed length of time being exceeded. Kind of like filling up a pitcher too much, and it overflows just a bit.
I think this is how we understand what she’s written, and how we generalize across time and space.
The ‘label’ might actually be a number or series of numbers, derived from the above breakdown.
The way we understand ideas, at multiple levels and in multiple contexts, does not seem all that dissimilar from convolutional scanning.
Hi,
Thanks for letting us know of such a great work.
I’m curious to know what web technologies are used to develop such interactive UI for the platform.ai. The reason I’m asking is that one of the application for which we developed the DL models required a similar kind of UI. The interactions are key for the application.
Any hints will be greatly appreciated.
Thx.
In case you are interested Jeremy talked about platform.ai on his Full stack deeplearning. I think it showcases how amazing platform.ai is.
1 Like
Thanks Daniel. It is indeed a very good talk.
I can’t signup/login with gmail or github account. when i login, a loader appears and then i get redirected to home page… is it only me or you guys Removed this app or something…?
P.S i also tried changing accounts and even browser… same issue. i am on macbook.
Try clearing your cookies first. That usually works.
Also Chrome is the recommended browser.
I just found out you guys have changed policy
I got an email
“We have changed our access policies and no longer support free accounts except for members of our fellowship program and corporate trials.”
I have applied for fellowship. but it looks like that will be a time taking process.
Anyways, this tool really looks good though and Everyone would Love to try it… Is there any other way. like a paid account of maybe i can ask my corporation to register somewhere for trial etc…?