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

Deep Learning Interviews book: Hundreds of fully solved job interview questions

github.com

Post reply on HN
Print view View original

131–140 of 157 posts

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#131

Post by uoaei »

light_hue_1 wrote: post #127
uoaei wrote: post #53

Earlier quoted context omitted.

In part because ML fails silently by design. Even if the code runs flawlessly with no errors, the outputs could be completely bunk, useless, or even harmful, and you won't have any idea if that is true just from watching The Number go down during training. It's not enough to know how to build it but also how it works . It's the difference between designing the JWST and assembling it.

And you learn literally zero about a candidate's ability to understand when and why things work by asking questions about eigenvectors. Someone can understand what an eigenvector is and still not have any clue about how you figure out a system is working, why it's working, what is likely to happen in production, how you test the limits of your method's ability to generalize, how you take an real problem and find some…

The "trivia" tests, when used (IMO) correctly, are not for testing whether or not the candidate recognizes the term and can regurgitate a definition. I prefer to listen to how they phrase their response to get a sense of the intuition behind the understanding of the concept as well as how it may fit in to a larger mathematical framework (i.e. their internal model for mathematical analysis).

I am not looking for someone to answer the question correctly, but to answer the question in a way that demonstrates deeper insights, which helps immensely in research settings as re-using properties of mathematical constructs in novel ways is often how theory and practice both are advanced.

I would be much less interested in someone giving a precise definition of eigenvalues than to describe them in such a way that they understand e.g. what can be deduced about an operator when one of its eigenvalues is zero.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#132

Post by uoaei »

mattkrause wrote: post #83
uoaei wrote: post #53

Earlier quoted context omitted.

In part because ML fails silently by design. Even if the code runs flawlessly with no errors, the outputs could be completely bunk, useless, or even harmful, and you won't have any idea if that is true just from watching The Number go down during training. It's not enough to know how to build it but also how it works . It's the difference between designing the JWST and assembling it.

I'm sure this happens, but do you think the problem is actually one of mathematical savvy? My guess would be that more machine learning projects go off the rails for want of understanding the data or the {business, research} problem.

Not necessarily mathematical savvy though a lot of deeper understanding can follow from a strong grasp on the fundamentals. I think it has more to do with the alignment between intuitions and outcomes, and this is not taught well in most academic programs as far as I can tell.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#133

Post by angarg12 »

coconut_man wrote: post #130
angarg12 wrote: post #88

I have been working as an ML Engineer for a few years now and I am baffled by the bar to entry for these positions in the industry. Not only I need to perform at the Software Engineer level expected for the position (with your standard leetcode style interviews), but I need to pass extra ML specific (theory and practice) rounds. Meanwhile the vast majority of my work consist of getting systems production ready and hu…

just like Software Engineer having to pass leetcode round and system design round, I also doubt that ML theory and practice is much harder than system design (theory and practice). Beside that, you get paid more than Software Engineer.

I can tell you we are not paid more than Software Engineers, but that might be only my company.

One startup asked me this. They gave me a very vague problem statement, and in 2 days I had to find a couple of recent articles relevant to the problem and prepare a presentation explaining my solution and justifying my decisions.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#134

Post by uoaei »

borroka wrote: post #65
uoaei wrote: post #53

Earlier quoted context omitted.

In part because ML fails silently by design. Even if the code runs flawlessly with no errors, the outputs could be completely bunk, useless, or even harmful, and you won't have any idea if that is true just from watching The Number go down during training. It's not enough to know how to build it but also how it works . It's the difference between designing the JWST and assembling it.

But the OP was asking something different, that is why someone should excessively focus on theory, when, by the way, DL theory is very far from being solid and trial and error in ML and AI is the common way of operating. The "model is in place, but I have no clue what's doing and so it can fail without me understanding when and how is straw-man". Especially for supervised learning, that is, we have a label for data,…

You are considering only the technical aspects of the model. While of course important to understand, those are less interesting when considering potential harms than the downstream effects of the inference pipeline, particularly when it comes to interpretations of outputs. What is absolutely the worst possible MO is to offload the interpretation portion of a pipeline to a machine using proxy metrics without an exceptional model which justifies the approach unequivocally.

For instance, if we put an MSE loss function on a classification NN with sigmoid outputs, and used a classification dataset, we could generate an entire zoo of "many, many very accurate models" as measured by MSE. But once your model returns outputs, how do you interpret them to predict a label for some input data? You could hack some algorithm together (eg argmax of the highest value) which is indistinguishable from the "correct" procedure but the described probabilities are so incorrect that no ML professional would be comfortable trusting anything it says, not least because of the violation of the condition that the probabilities are non-negative and sum to one. But being able to explain why we use MSE or cross-entropy or any other loss function and which output activations (hint: and probability distributions) they are typically associated with actually has a very deep origin in the foundations of probability theory which blows open a whole new way of thinking about statistical modelling that is not made available in any of the programs whose materials I've been exposed to.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#135

Post by angarg12 »

capdeck wrote: post #103
angarg12 wrote: post #88

I have been working as an ML Engineer for a few years now and I am baffled by the bar to entry for these positions in the industry. Not only I need to perform at the Software Engineer level expected for the position (with your standard leetcode style interviews), but I need to pass extra ML specific (theory and practice) rounds. Meanwhile the vast majority of my work consist of getting systems production ready and hu…

> ... I'll seriously consider a regular non-ML position. What about asking for more money at the end? Multi-stage complex interview process eliminates more candidates. Some, like you say, will opt for a developer gig instead, probably because ML wasn't something they were interested in to begin with. That narrows down the list of candidates even more. Either "play the game" and ask for more money or don't play the ga…

If what I want is money I think I'm better off getting competing offers as a regular Software Engineer and pumping the numbers.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#136

Post by uoaei »

dekhn wrote: post #109
uoaei wrote: post #53

Earlier quoted context omitted.

In part because ML fails silently by design. Even if the code runs flawlessly with no errors, the outputs could be completely bunk, useless, or even harmful, and you won't have any idea if that is true just from watching The Number go down during training. It's not enough to know how to build it but also how it works . It's the difference between designing the JWST and assembling it.

ML doesn't just fail silently by design. because ML is based on error minimization, it fails in a way that is maximally hard to tell from random garbage. This is, remarkably, a subtlety that is lost on most people, which is a real surprise- my introduction to this was in structural biology, where you always do hold-outs and check the performance on the hold-out set before overfitting is such a problem.

Absolutely, the result you get is "the best you can do given the baked-in assumptions". But of course the assumptions can be wrong. And it takes time to learn how to evaluate and revise your assumptions in any analytical field, hard or soft.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#137

Post by Raphaellll »

ruph123 wrote: post #63
Raphaellll wrote: post #38

I actually bought this as a physical book on Amazon. Naturally it came as a print-on-demand book. Unfortunately it has many problems in this format. E.g. the lack of margins makes it hard to read the end of sentences towards the gutter. Also some text is pushed into each other. Not sure what source file format you have to provide to Amazon, but it's certainly not the pdf provided in the repo. Edit: It seems the overl…

The last 5 textbooks I bought new on amazon had similar problems. Totally unacceptable. I started returning them and (because most were exclusive to amazon) started buying them new on ebay with great results.

It's really a hit and miss. This [1] book also came as print-on-demand but looks perfectly fine. Good layout and clean colors.

[1] https://mml-book.github.io/book/mml-book.pdf

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#138

Post by disgruntledphd2 »

jstx1 wrote: post #27
disgruntledphd2 wrote: post #21

Earlier quoted context omitted.

Facebook Product Data Science has always been a Product Analyst role more than anything else. I did the interviews a while back, and it was a pretty fun experience, but it's not what a lot of people call data science.

> but it's not what a lot of people call data science I think that's changed a bit over time and the term has expanded to mean more things. In addition to Facebook, another great example is this article from Lyft in 2018 where they say that they're renaming all their data analysts to data scientists and all their data scientists to research scientists - https://medium.com/@chamandy/whats-in-a-name-ce42f419d16c

This is called title inflation.

Like the hilarious thing about Facebook and Data Science is that the term was invented there, and they needed to retitle all of their analysts (like Product Data Science) as they couldn't hire any analytical people with an analyst title in SV (or so I have been told).

Like, data science was defined back in the days as a social science PhD who could run experiments and write MapReduce jobs. I'm pretty sure that most people would disagree with this definition these days.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#139

Post by medstrom »

master_yoda_1 wrote: post #33
coliveira wrote: post #20

Earlier quoted context omitted.

Do you have any books/material that can help the learner acquiring this deeper understanding?

I know one good reference. https://www.deeplearningbook.org/ Also there are various courses and lectures but that needs time and effort. There is no short cuts like the book posted by OP.

I believe "shortcut books" like the one posted by OP appeal to some of us because it's a succinct source of, basically... lookup queries. That is, when we run across a question we can't answer, we'd prefer to Google that topic on our own and learn in our own nonlinear style. Don't give me a pile of textbooks corresponding to 6-10 semesters of classes, give me a single book like this and let me research by myself everything it refers to.

Re: Deep Learning Interviews book: Hundreds of fully solved job interview questions

#140

Post by krageon »

kragen wrote: post #77
minimaxir wrote: post #74

Earlier quoted context omitted.

If that's the case for the DS/ML domain, then a short take-home exam should provide a better example of practical coding ability (the common counterargument that "take-home exams can be gamed" is a strawman that would be more on the interviewer's fault for creating a flawed exam). In my case, I typically got the "implement binary search" questions in a technical interview after I passed a take-home exam, which just m…

Agreed. If you're gaming the take-home exam by looking up the answer on Stack Overflow, you could game the same exam in person by reading books of interview questions ahead of time, and the interviewer can avoid that by making up new questions. (OTOH if you're gaming the take-home exam by paying someone else to solve the problem for you, that might be harder to tell.)

Why is that gaming the exam? What sort of professional doesn't look up the solutions to potential problems online, even if it is just to verify that you're correct? Outside of incredibly trivial things, I would expect this of everyone.
Post reply on HN