elvis Profile picture
11 Nov, 8 tweets, 1 min read
Imagine you are in a machine learning interview and want to share your experience building deep learning projects. Don’t try to impress your interviewer by telling them how you applied a Transformer-* and got 99% accuracy. Instead, discuss the following:

[Thread]

1/8
Motivate the problem and why you want to address it? Include an impact statement (Showcase due diligence)

2/8
What is the research/business objective (Showcase rigor and focus)

3/8
What has been done, ideas you are adapting, and your action plan (Showcase project management skill)

4/8
How did you collect/clean/prepare the data? Share details about your basic model/baseline? Share challenges? Experience with experiments? Metrics used? (Showcase hands-on experience and versatility)

5/8
Explains the challenges with inference/data/scaling/applicability/trade-offs/costs of model building/training and how you addressed them. (Showcase problem solving)

6/8
Share your experience working with the team. Don't focus too much on what they did, but what **you** contributed to the effort. (Showcase your expertise)

7/8
What did you learn from the experience and how do you plan to improve the process/model? What are the next steps? (Showcase desire to keep adapting and learning)

8/8

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with elvis

elvis Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @omarsar0

13 Nov
In case you missed them, here is a thread (in no special order) of some machine learning guides and lists of recommendations I have carefully put together over the last few weeks.

I hope they are useful. Feedback is always appreciated.

Happy Learning! 🎓

[Thread] ImageImageImageImage
⭐️ Getting Started with Applied ML Research

I strongly believe that applied ML research is just as important as theoretical research. Learn ways how to get started with applied ML research.

elvissaravia.substack.com/p/getting-star… Image
⭐️ My Recommendations to Learn Mathematics for Machine Learning

Maths is fundamental to learning and building deeper intuitions about machine learning methods. This article includes my recommendations on resources where you can get started.

elvissaravia.substack.com/p/my-recommend… Image
Read 7 tweets
12 Nov
Lots of people believe that to do ML engineering you don’t need to know maths. In my experience, this is simply not true.

I learned this the hard way in my first big interview for a deep learning engineering post with a big AI company (won’t say the name here).

1/4
Specifically, I was asked to calculate the derivative of a variant of a popular activation function and implement it with Python.

Note that this was for an internship position. Just learn some math for ML and improve your chances to do well in interviews. Take your time.

2/4
This was in the interview phase. It could be that you won't need those math skills in your actual day to day job. However, companies that are innovating with ML methods are constantly exploring new ideas that may just require what I was asked to do in that interview.

3/4
Read 4 tweets
5 Nov
People often ask me how to build better intuitions about different machine learning and deep learning methods. This is a thread about my experience (as an NLP Researcher) building better intuitions of ML/deep learning methods, including resources and tips.

🧵
Overview -- Building intuitions about concepts related to a field requires investing a lot of time and effort. For ML, it is no different. In this thread, I will share a bit of my journey and personal experience building intuitions about DL/ML algorithms & new research ideas.
I don't claim that the tips I share here will work for everyone. Doing a Ph.D. gave me enough time to explore ways to dig deeper into topics, so the context matters. I had access to great advisors that provided me a learning path to be productive in learning and building things.
Read 20 tweets
23 Oct
Before you jump into deep learning, I would strongly advise you to do a few introductory machine learning courses to get up to speed with fundamental concepts like clustering, regression, evaluation metrics, etc.

Here is a thread including a few recent courses you can explore:
"Create machine learning models"

by Microsoft

Note: the module on clustering is really good!

docs.microsoft.com/en-gb/learn/pa…
"Stanford CS229: Machine Learning"

by Stanford and Andrew Ng

Note: One of my favorite ML courses of all time!

youtube.com/playlist?list=…
Read 10 tweets
13 Oct
I have always emphasized on the importance of mathematics in machine learning.

Here is a compilation of resources (books, videos & papers) to get you going.

(Note: It's not an exhaustive list but I have carefully curated it based on my experience and observations)
📘 Mathematics for Machine Learning

by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong

mml-book.github.io

Note: this is probably the place you want to start. Start slowly and work on some examples. Pay close attention to the notation and get comfortable with it.
📘 Pattern Recognition and Machine Learning

by Christopher Bishop

Note: Prior to the book above, this is the book that I used to recommend to get familiar with math-related concepts used in machine learning. A very solid book in my view and it's heavily referenced in academia.
Read 9 tweets
11 Oct
It's really concerning to see so much false advertisement on this idea that applying machine learning is easy.

I talk from both a research and application perspective. The process is rigurous. It's highly iterative and that should give you a hint of why it's hard.
There is rarely a straightforward answer on how to properly apply ML algorithms to dynamic real world datasets. It's a lot of experimentation. First, you need to organize and understand your data very well.

A good experimentation framework helps but that's just the beginning.
A lot of the toy datasets and problems used to teach ML today are clean and binary.

Things in the real world are rarely binary.

You need to spend time cleaning and understanding your data and in some cases dealing with other aspects of it like access, control, privacy,...
Read 10 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!