Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A non-technical explanation of deep learning

parand.com

Post reply on HN
Print view View original

101–110 of 139 posts

Re: A non-technical explanation of deep learning

#101

Post by freedomben »

mrbombastic wrote: post #76
gregschlom wrote: post #73

Earlier quoted context omitted.

Maybe GP is a non-native English speaker? This construct would be pretty common way for a native French speaker to say they are angry at something. Not sure if it's common in English as well.

This is a pretty common phrase in English as well, it is not meant to be taken literally.

Yep, it may be more common in some English-speaking cultures, but in the midwest of the US it's extremely common to say stuff like, "I'll never forgive him for " and it's not meant to be taken literally. A more literal translation would be, "I'm very disappointed in this person's decision to ."

Re: A non-technical explanation of deep learning

#103

Post by kaycebasques »

gnicholas wrote: post #60
jstx1 wrote: post #23

Does stuff like this help anyone? I still haven’t forgiven CGP Grey for changing the title to his 2017 ML video to “How AIs, like ChatGPT, learn”. The video is about genetic algorithms and has nothing to do with ChatGPT. (or with anything else in modern AI)

I read this to see if it would be useful to share with my 9 year old. After reading it, I think it is not any more useful (alone) than watching the 3b1b video on this topic. The video is longer, but has more visualizations. I think that perhaps reading this description after watching the video might make the process more memorable. My guess is that if I had my daughter read this first, it wouldn't do much to make the…

> I think it is not any more useful (alone) than watching the 3b1b video on this topic

This one? https://youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_...

Re: A non-technical explanation of deep learning

#104

Post by cshimmin »

GaggiX wrote: post #25
time_to_smile wrote: post #21

Earlier quoted context omitted.

Don't love it, it's not correct. > what the reward / punishment system really equates to Nothing, and least as far as neural network training goes. This is an extremely poor analogy regarding how neural networks learn. If you've ever done any kind of physical training and have had a trainer sightly adjust the position of your limbs until what ever activity you're doing feels better, that's a much closer analogy. You'…

>There's nothing analogous to a "reward" or "punishment" when neural networks are learning. Well deep reinforcement learning.

Yeah but even in that case, "reward" is just the thing a NN is trying to predict. The NN itself is not receiving the reward (or any punishment). Instead, it's following gradient signals to improve that estimate of reward, which is then used as a proxy for an optimal policy decision.

Re: A non-technical explanation of deep learning

#105

Post by cshimmin »

mr_toad wrote: post #97
_gmax0 wrote: post #45

The most concise and intuitive line of explanation I've been given goes along the lines of this: 1 - We want to model data, representative of some system, through functions. 2 - Virtually any function can be expressed by a n-th order polynomial. 3 - We wish to learn the parameters, the coefficients, of such polynomials. 4 - Neural networks allow us to brute-force test candidate values of such parameters (finding opti…

> Virtually any function can be expressed by a n-th order polynomial. But there are many things that are not functions. Like circles. And they tend to crop up a lot in the real world, no pun intended.

Well, technically a circle can't be said to be a function but not for the reason you mean. A circle is a collection or a set of points, for example in a 2d plane, that are equidistant from a center point.

Probably what you are trying to say is that "a circle is not the image of a function", but that is also not true. You're assuming since in cartesian coordinates you can solve for y = +/- sqrt(R^2 - x^2), the fact that y is multi-valued means it's not a function. This is what they teach in highschool pre-calculus anyway.

But for example, we can associate the points on a circle with the image of the function e^{i theta}. Or equivalently, with the R^2-valued function f(theta) = (cos(theta), sin(theta)).

Re: A non-technical explanation of deep learning

#106

Post by ChatGTP »

gnicholas wrote: post #60
jstx1 wrote: post #23

Does stuff like this help anyone? I still haven’t forgiven CGP Grey for changing the title to his 2017 ML video to “How AIs, like ChatGPT, learn”. The video is about genetic algorithms and has nothing to do with ChatGPT. (or with anything else in modern AI)

I read this to see if it would be useful to share with my 9 year old. After reading it, I think it is not any more useful (alone) than watching the 3b1b video on this topic. The video is longer, but has more visualizations. I think that perhaps reading this description after watching the video might make the process more memorable. My guess is that if I had my daughter read this first, it wouldn't do much to make the…

Sorry if this is a personal question, but why would you get a 9 year old into machine learning ?

Re: A non-technical explanation of deep learning

#107

Post by cshimmin »

time_to_smile wrote: post #3

> This is how neural networks work: they see many examples and get rewarded or punished based on whether their guesses are correct. This description more closely describes reinforcement learning, rather than gradient based optimization. In fact, the entire metaphor of a confused individual being slapped or rewarded without understanding what's going on doesn't really make sense when considering gradient optimization…

Well said re: gradient optimization vs. "getting slapped". However, note that since NN optimization is almost always nonconvex, we are NOT guaranteed to arrive an a optimal (or even close-enough) solution. A major limitation of gradient based optimization on nonconvex problems is that they are very susceptible to getting trapped in local minima.

But, for now it's the best tool we have, so we just have to hope that we get close enough, or just empirically run lots of times to find the best local minimum we can. Incidentally, this actually is more like a brute-force approach, but at the ensemble level, which is quite different than the article means it.

Re: A non-technical explanation of deep learning

#108

Post by cshimmin »

adrianmonk wrote: post #24
nailer wrote: post #14

Earlier quoted context omitted.

Most non technical people would think there are zero circumstances where a spreadsheet could be a cat.

It's obvious from context that it's the content of the media. To me at least. If I play you a song on Spotify and say, "Is this a saxophone?", you wouldn't say, "No, it's a iPhone running Spotify." If a policeman holds up a photograph of a person and says, "Is this the person who attacked you?", the victim doesn't say, "No, it's an 8 by 10 glossy print."

mais ceci n'est pas une pipe!

Re: A non-technical explanation of deep learning

#109

Post by gibolt »

ChatGTP wrote: post #106
gnicholas wrote: post #60

Earlier quoted context omitted.

I read this to see if it would be useful to share with my 9 year old. After reading it, I think it is not any more useful (alone) than watching the 3b1b video on this topic. The video is longer, but has more visualizations. I think that perhaps reading this description after watching the video might make the process more memorable. My guess is that if I had my daughter read this first, it wouldn't do much to make the…

Sorry if this is a personal question, but why would you get a 9 year old into machine learning ?

Why not? Get them into a little bit of everything, and let them dig further into the topics that they find exciting.

Kids are just as capable as most adults (if not more). Give them a foot in the door and they have all the time in the world to build in that knowledge.

Post reply on HN