Hacker News new | comments | show | ask | jobs | submit | robrenaud's comments login

I don't know that they physics analogy works so well, or at least, it's definitely missing something. What prevents the whole word "universe" from collapsing on itself, forming a black hole? That is, if there are only attractive forces, the global optimum is to co-locate everything in the same point, which doesn't give you a useful model. There needs to be something in the model that keeps different words apart from each other.

This page has the clearest explanation of word embeddings and the relationship between the objective function and why vector translation captures meaning.

http://nlp.stanford.edu/projects/glove/


in real world, gravitational force appears on every object.

in the word2vec world, it only appears on words found in similar context. that's one major difference.

I think there is also anti-gravitational force that pushes words away. but again I need to double check.


it works because the gravity of word2vec isn't the gravity of real life.

notice that I only pull the word "dog" to the center of gravity of the rest words, instead of pulling all of them together. I think the full version even push the rest of the words away from the center of gravity.

but I need to double check the math.

this is not just an analogy. this is what word2vec's math says.

the only analogy part is that word2vec is in high dimension, my analogy is in 3 dimension.


As far as I can tell, this isn't even in a nice part of New York.

-----


It's a working class Caribbean neighborhood right now but was originally built as housing for middle-class Victorian clerics, so there's a lot of beautiful but run down buildings & great transport links (ie. ripe for gentrification).

In the 90s it was extremely rough (race riots), now it's fairly safe and the artisanal coffee shops and trendy restaurants are creeping southwards as the city's population continues to grow & get priced out of other areas.

Guessing a flop house packed with affluent young tech bros is going to throw some gasoline on the Crown Heights hyper-gentrification fire, for better or worse.

-----


Would Twitter's Innovator's Patent agreement have worked out better for him?

-----


Well, the hiring committees see the entire prior rating distribution from each interviewer as well as the hires/no hires for each previous rating.

So the committees has a decent way of correcting for interviewers who use different scales.

-----


Right. You'd only know someone was "hard to impress" with that information.

-----


This is probably very context dependent, because I've learned the opposite.

For example, I was rewriting/consolidating a corner of the local search logic for Google that was spread throughout multiple servers in the stack. Some of the implementation decisions were clearly made because of the convenience of doing so in a particular server. But when consolidating the code into a single server, the data structures and partial results available were not the same, so re-producing the exact same logic and behavior would have been hard. Realizing which parts of the initial implementation were there because it was convenient, and which were there for product concerns let me implement something much simpler that still satisfied the product demands, even if the output was not bitwise identical.

-----


I didn't read the parent comment as reproducing the exact same logic perfectly. More as a definition of the interface between the external code and the part to replace and matching that interface closely with the replacement.

This isn't always possible but seems like a reasonable objective given my experience.

-----


Here is a paper that audio and video for speech recognition, and they find that video helps especially in noisy environments.

https://www.uni-ulm.de/fileadmin/website_uni_ulm/allgemein/2...

-----


Awesome!

Noisy environments are exactly when seeing the lips is a huge deal for me. I have a friend who has a tendency to absent-mindedly place his hand in front of his mouth. In a quiet office or home, no issue. In a bar? He pressed mute, as far as I'm concerned.

-----


Apparently 107 billion humans have ever lived. 1% of that is greater than a billion.

http://www.bbc.com/news/magazine-16870579

> here are currently seven billion people alive today and the Population Reference Bureau estimates that about 107 billion people have ever lived.

That said, merely being in the top 1% of intelligence doesn't seem to be worthy of the genius title.

-----


If you are in the top 1% or even 5% you are probably capable of genius things if given the opportunity. The majority never are.

Genius is much more common than opportunity.

-----


How do i up vote this. I have the genius but lacking the opportunity i think

-----


> That said, merely being in the top 1% of intelligence doesn't seem to be worthy of the genius title.

Especially considering that the population average in many places and times is far below the current population averages normed in the USA and UK and Western Europe. If you asked how many people throughout history or globally would be in the top 1% of the USA/UK/WE population, the answer will be much smaller than a billion. (Thin tails strike again.)

-----


What if your MAC addresses aren't spread that far between each other?

-----


What about it? Remember, we're no longer using a hash function on anything - we don't want the numbers to be uniformly spread on any range - just unique.

-----


I love having the ATM around, in the train station, in the convenience store, etc.

But the entire bank attached to the ATM has almost no value. I think I've talked to a real live person in a bank like twice in the last three years.

-----


Does it matter?

Sure, consider that $10k or whatever that you need for a couple months after you lose your job. In an economic downturn, if your stocks/bonds lose half their value, it costs you $20k of pre downturn, investment dollars rather than the $10k of pre-down turn dollars if the money was in a savings account.

-----

More

Applications are open for YC Summer 2016

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | DMCA | Apply to YC | Contact

Search: