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

21–30 of 157 posts

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

#21

Post by disgruntledphd2 »

jstx1 wrote: post #14
minimaxir wrote: post #9

Earlier quoted context omitted.

The hard questions in DS/ML interviews I've received over the years aren't the theory questions (which I rarely get asked), but the trick SQL questions that often depend on obscure syntax and/or dialect-specific features, or "implement binary search" when I'm not in the mindset for that as that isn't what DS/ML is in the real world.

I think they're fine as long as you know the format and have an opportunity to prepare or just get in the right mindset for it. And some things (like binary search) should be easy to write anyway. The SQL questions can also be a symptom of the type of job - Facebook's first data science round focuses a lot on SQL but that's because it's a very product/analytics/decision-making focused role without that much coding or…

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.

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

#22

Post by 8note »

1970-01-01 wrote: post #6

This book has fun problems! Example: During the cold war, the U.S.A developed a speech to text (STT) algorithm that could theoretically detect the hidden dialects of Russian sleeper agents. These agents (Fig. 3.7), were trained to speak English in Russia and subsequently sent to the US to gather intelligence. The FBI was able to apprehend ten such hidden Russian spies and accused them of being "sleeper" agents. The A…

Really small?

How many russians in america are actually sleeper agents?

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

#23

Post by disgruntledphd2 »

time_to_smile wrote: post #19
mrfusion wrote: post #11

Are there deep learning roles that focus more on software engineering and using the tools rather than having a deep understanding of statistics?

> having a deep understanding of statistics? As someone with a strong background in statistics, please tell me where I can find DS jobs that require this. For me and all my statistics friends in DS we find much more frustration in how hard it is to pass DS interviews when you understand problems deeper than "use XGBoost". I have found that very few data scientists really even understand basic statistics, I failed an…

A good conceptual understanding of statistics is always helpful.

It's not really tested for in most places though, where they regard a DS as a service that produces models.

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

#24

Post by thaumasiotes »

kilotaras wrote: post #8
1970-01-01 wrote: post #6

This book has fun problems! Example: During the cold war, the U.S.A developed a speech to text (STT) algorithm that could theoretically detect the hidden dialects of Russian sleeper agents. These agents (Fig. 3.7), were trained to speak English in Russia and subsequently sent to the US to gather intelligence. The FBI was able to apprehend ten such hidden Russian spies and accused them of being "sleeper" agents. The A…

Bayes rule with odd ratios makes it pretty easy. base odds: 20:80 = 1:4 relative odds = (1 letter/6 letters) : (2 letters / 8 letters) = 2/3 posterior odds = 1:4*2:3 = 1:6 Final probability = 1/(6+1) = 1/7 or roughly 14.2% Bayes rule with raw probabilities is a lot more involved.

Odds are usually represented with a colon -- the base odds are 1:4 (20%), not 1/4 (25%).

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

#25

Post by minimaxir »

jstx1 wrote: post #14
minimaxir wrote: post #9

Earlier quoted context omitted.

The hard questions in DS/ML interviews I've received over the years aren't the theory questions (which I rarely get asked), but the trick SQL questions that often depend on obscure syntax and/or dialect-specific features, or "implement binary search" when I'm not in the mindset for that as that isn't what DS/ML is in the real world.

I think they're fine as long as you know the format and have an opportunity to prepare or just get in the right mindset for it. And some things (like binary search) should be easy to write anyway. The SQL questions can also be a symptom of the type of job - Facebook's first data science round focuses a lot on SQL but that's because it's a very product/analytics/decision-making focused role without that much coding or…

> And some things (like binary search) should be easy to write anyway.

It's a different story when a) your mind is set on statistics/linear algebra b) you've never had to actually implement binary search by hand since college and c) even if you do implement the algorithm and demonstrate that you have a general understanding, it must work perfectly and pass test cases otherwise it doesn't count.

FWIW I was rarely asked about algorithmic complexity which is more relevant in DS/ML, albeit it's usually in the context of whiteboarding another algorithm and the interviewer mocking me for doing it in O(n) instead of O(logn).

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

#26

Post by Aethylia »

kilotaras wrote: post #8
1970-01-01 wrote: post #6

This book has fun problems! Example: During the cold war, the U.S.A developed a speech to text (STT) algorithm that could theoretically detect the hidden dialects of Russian sleeper agents. These agents (Fig. 3.7), were trained to speak English in Russia and subsequently sent to the US to gather intelligence. The FBI was able to apprehend ten such hidden Russian spies and accused them of being "sleeper" agents. The A…

Bayes rule with odd ratios makes it pretty easy. base odds: 20:80 = 1:4 relative odds = (1 letter/6 letters) : (2 letters / 8 letters) = 2/3 posterior odds = 1:4*2:3 = 1:6 Final probability = 1/(6+1) = 1/7 or roughly 14.2% Bayes rule with raw probabilities is a lot more involved.

Assuming that the algorithm is 100% accurate!

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

#27

Post by jstx1 »

disgruntledphd2 wrote: post #21
jstx1 wrote: post #14

Earlier quoted context omitted.

I think they're fine as long as you know the format and have an opportunity to prepare or just get in the right mindset for it. And some things (like binary search) should be easy to write anyway. The SQL questions can also be a symptom of the type of job - Facebook's first data science round focuses a lot on SQL but that's because it's a very product/analytics/decision-making focused role without that much coding or…

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

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

#28

Post by hervature »

kilotaras wrote: post #8
1970-01-01 wrote: post #6

This book has fun problems! Example: During the cold war, the U.S.A developed a speech to text (STT) algorithm that could theoretically detect the hidden dialects of Russian sleeper agents. These agents (Fig. 3.7), were trained to speak English in Russia and subsequently sent to the US to gather intelligence. The FBI was able to apprehend ten such hidden Russian spies and accused them of being "sleeper" agents. The A…

Bayes rule with odd ratios makes it pretty easy. base odds: 20:80 = 1:4 relative odds = (1 letter/6 letters) : (2 letters / 8 letters) = 2/3 posterior odds = 1:4*2:3 = 1:6 Final probability = 1/(6+1) = 1/7 or roughly 14.2% Bayes rule with raw probabilities is a lot more involved.

I don't know about "a lot more". It is essentially the same calculation without having to know 3 new terms. Let:

A = the event they are a spy B = the event that an l appears

And ^c denote the complement of these events. Then,

P(A) = 1/5

P(A^c) = 4/5

P(B|A) = 1/6

P(B|A^c) = 1/4

P(A|B) = P(B|A)P(A)/P(B)

By law of total probability,

P(B) = P(B|A)P(A) + P(B|A^c)P(A^c)

Which is very standard formulation and really just your equation as you can rewrite everything I have done as:

P(A|B) = 1/(1 + P(B|A^c)P(A^c)/P(B|A)P(A))

Which is the base odds, posterior odds, and odds to probability conversion all in one. The reason why this method is strictly better in my opinion is because the odds breaks down simply if we introduce a third type of person which doesn't pronounce l's. Also, after doing one homework's worth of these problems, you just skip to the final equation in which case my post is just as short as yours.

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

#29

Post by FabHK »

kilotaras wrote: post #8
1970-01-01 wrote: post #6

This book has fun problems! Example: During the cold war, the U.S.A developed a speech to text (STT) algorithm that could theoretically detect the hidden dialects of Russian sleeper agents. These agents (Fig. 3.7), were trained to speak English in Russia and subsequently sent to the US to gather intelligence. The FBI was able to apprehend ten such hidden Russian spies and accused them of being "sleeper" agents. The A…

Bayes rule with odd ratios makes it pretty easy. base odds: 20:80 = 1:4 relative odds = (1 letter/6 letters) : (2 letters / 8 letters) = 2/3 posterior odds = 1:4*2:3 = 1:6 Final probability = 1/(6+1) = 1/7 or roughly 14.2% Bayes rule with raw probabilities is a lot more involved.

Hmm, a bit more involved maybe, but not that much. But your calculation sure seems short.

With S = sleeper, and L = letter L, and remembering "total probability":

   P(L) = P(L|S)P(S) + P(L|-S)P(-S),
(where -S is not S), we have by Bayes

   P(S|L)
 = P(L|S) P(S) / P(L)
 = P(L|S) P(S) / (P(L|S)P(S) + P(L|-S)P(-S))
 = 1/6 * 1/5 / (1/6*1/5 + 1/4*4/5) 
 = 1/30 / (1/30 + 6/30) 
 = 1/7
Post reply on HN