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

71–80 of 139 posts

Re: A non-technical explanation of deep learning

#71

Post by wanderlust123 »

zvmaz wrote: post #31

I have met people who think they understand a particular topic I am versed in, but actually don't. Similarly, I am often wary that I get superficial knowledge about a topic I don't know much about through "laymen" resources, and I doubt one can have an appropriate level of understanding mainly through analogies and metaphors. It's a kind of "epistemic anxiety". Of course, there are "laymen" books I stumbled upon whic…

Can you please suggest other books similar in spirit to the Nagel book? Would love to read some over summer

Re: A non-technical explanation of deep learning

#72

Post by lhnz »

I have a few funny analogies that I think kind of work.

1. "gradient descent" is like tuning a guitar by ear and listening to the beat frequencies ("loss") and then decreasing these by tuning a string up or down.

2. the best I can come up with for "backpropagation" is to imagine a clever device that can tirelessly optimize a Rube Goldberg machine for you but as a science, not an art.

Re: A non-technical explanation of deep learning

#73

Post by gregschlom »

Trufa wrote: post #70
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)

What a strange word to use in that context, why would he need to be forgiven by you? How has he wronged you? Seems at worst, an honest mistake in a complicated topic.

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.

Re: A non-technical explanation of deep learning

#74

Post by mcbuilder »

0xBABAD00C wrote: post #40
clarle wrote: post #33

Totally aware that this isn't a fully formal definition of deep learning, but one interesting takeaway for me is realizing that in a way, corporations with their formal and informal reporting structures are structured in a way similar to neural networks too. It seems like these sort of structures just regularly arise to help regulate the flow of information through a system.

There is research claiming the entire universe is a neural network: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7712105/

That's the sort of blue sky research I'm glad exists.

Re: A non-technical explanation of deep learning

#75

Post by romwell »

Myrmornis wrote: post #68

> they see 3 spreadsheets of numbers representing the RGB values of the picture. This needs expanding: it's the sort of thing that's easy for a programmer to say, but few non-{programmer,mathematically trained person} are going to see that an RGB value has 3 parts and so a collection of RGB values could be sliced into 3 sheets.

...or know what Ruth Ginsburg Bader has anything to do with it all.

The RGB color model and representation of images in it is already technical. Anyone who knows what it means also wouldn't need to be told the following quip:

>Also note that computers see things as multi-dimensional tables of data. They don't look at a "picture" - they see 3 spreadsheets of numbers representing the RGB values of the picture.

...which is the only time RGB is mentioned in the article.

That's before we get to the part that "multidimensional" here is extraneous, and doesn't even match the typical usage (where RGBA is stored as a single 32-bit value). Everything is a tape of 1's and 0's, "multidimensionality" comes from interpretation of data.

The dimension of image data is still 2: each pixel is a sample a 2D projection of a 3D world, and is related to other pixels in a way that's different than, say, those of letters in a line of text, or voxels (letters don't have a a well-defined "up" neighbor, voxels have more well-defined neighbors than pixels do).

Re: A non-technical explanation of deep learning

#76

Post by mrbombastic »

gregschlom wrote: post #73
Trufa wrote: post #70

Earlier quoted context omitted.

What a strange word to use in that context, why would he need to be forgiven by you? How has he wronged you? Seems at worst, an honest mistake in a complicated topic.

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.

Re: A non-technical explanation of deep learning

#77

Post by Cpoll »

Trufa wrote: post #70
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)

What a strange word to use in that context, why would he need to be forgiven by you? How has he wronged you? Seems at worst, an honest mistake in a complicated topic.

You're not using "at worst" correctly. What you describe is an "at best". Worse would be that CGP Grey deliberately picked a misleading title in order to optimize views, algorithm, etc.

This is, I think, the case. But I don't begrudge them too much, YouTube is cutthroat.

Re: A non-technical explanation of deep learning

#78

Post by hackernewds »

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…

You could just let your daughter see it. To what extent can you "protect" her exposure to the world?

Re: A non-technical explanation of deep learning

#79

Post by _gmax0 »

pedrosorio wrote: post #58
_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…

Mentioning polynomials is a pretty poor way to explain it for two reasons: - It requires some mathematical understanding so will exclude some part of the non-technical audience - It is the incorrect analogy. Non-linearities in neural networks have nothing to do with polynomials. In fact, polynomial regression is a type of linear regression, and for the most part, it sucks. Also, as someone mentioned, all the “serious…

Thanks for the correction. It's been some time since I actively thought about the theory (evidently I didn't digest it correctly the first time!).

Re: A non-technical explanation of deep learning

#80

Post by wrs »

cscurmudgeon wrote: post #56
wrs wrote: post #15

Earlier quoted context omitted.

I understand the Chinese Room argument to be that because the human in the room doesn’t understand Chinese, the system doesn’t understand Chinese. In this case, none of the humans can recognize cats, but the collective can.

Thats not the Chinese Room argument. The argument says just because a system processes X doesn't imply it has consciousness of X.

The flaw is the unsupported assertion that the whole system being conscious of X depends on a part of the system being conscious of X. The same assertion would fail here in the same way.
Post reply on HN