Parsa retweeted
I'd like to start 2024 with some thoughts on the state of optimization theory. To begin with, let me quote Nesterov's 2003 book:
"The main fact, which should be known to any person dealing with optimization models, is that, in general, the optimization problems are unsolvable"
🧵
Parsa retweeted
Fourier transform on groups turns convolution into multiplication. For non-commutative groups, it is matrix-matrix multiplication though … en.wikipedia.org/wiki/Fourie… en.wikipedia.org/wiki/Convol…
Parsa retweeted
Excited to be launching a series of short videos (5 min or less) to optimize the training performance of your PyTorch models!
Covering
- mixed-precision training
- multi-GPU training strategies
- Compiling PyTorch models
- and finding good batch sizes
🔗 lightning.ai/pages/courses/d…
Parsa retweeted
Replying to @marktenenholtz
I have not ever found better material in this topic than this course youtube.com/playlist?list=PL… from @rasbt Lectures from 8 to 12. The entre course is amazing but the model evaluation lectures are incredible.
Parsa retweeted
6 System Design Interview Questions
1. Instagram Design - bit.ly/3BqamCL
2. YouTube Design - bit.ly/3bbNnAN
3. URL Shortner - bit.ly/3bbNpZr
4. WhatsApp - bit.ly/3SbA9Eu
5. Parking Lot - bit.ly/3SaTyFM
4. LMS - bit.ly/3Jk9emc
Parsa retweeted
5 Software Engineering Practices to Become a Better Data Scientist by Frank Andrade buff.ly/3Irnmsb
Parsa retweeted
1. Jupyter Notebooks: youtube.com/watch?v=HW29067q…
2. Pandas: youtube.com/watch?v=e60ItwlZ…
3. Matplotlib: youtube.com/watch?v=nzKy9GY1…
4. Seaborn: youtube.com/watch?v=6GUZXDef…
Parsa retweeted
The Deep Learning Spring 2021 class materials are now fully available on the CDS website! cds.nyu.edu/deep-learning/
Parsa retweeted
My recommendations to start with machine learning math:
• Statistics 110: Probability — Harvard University
• Essence of Linear Algebra — 3Blue1Brown
• Multivariate Calculus — Coursera
Links and 3 additional free resources here: svpino.medium.com/are-you-re…
Parsa retweeted
I wrote about DeepMind's move into football, its work with Liverpool FC, and its attempts to create an automated virtual assistant coach, for @WiredUK
wired.co.uk/article/deepmind…
Parsa retweeted
10 advanced Python 🐍 concepts that you want to look into:
• Slicing
• Itertools
• Closures
• Lambdas
• Hashability
• Decorators
• Generators
• Concurrency
• Comprehensions
• Context managers
Would you add anything else to this list?
Parsa retweeted
Greatest things are accomplished when you keep on trying even when there is no hope at all. Never give up.
Parsa retweeted
If you want to learn Machine Learning and you don't want to wait for freeCodeCamp to finish the new Data Science curriculum... you don't have to.
@sannykimchi has built a cohesive sequence of free math and ML resources for you: Open ML University. curriculum.openmlu.com/
Parsa retweeted
Something essential for aspiring machine learning practitioners is to find an area where they can specialize and build their reputation.
I've met many people who focus on a specific niche and have built a career in it.
Here are some examples of things you could do:
↓ 1/5
Parsa retweeted
If you are looking to get a background in math before starting with machine learning, here is all the material you need covering the following topics:
• Probabilities & Statistics
• Linear Algebra
• Multivariate Calculus
More than enough to get started.
↓ 1/7
Parsa retweeted
About getting a job with machine learning, things you should do during an interview, and some random thoughts that may help you land a job
↓
Parsa retweeted
Working on problems is the best way to learn machine learning.
Here are 10 problems that can get you started.
▫️ From Kaggle
▫️ Already solved
▫️ Expanding different fields
▫️ Large community around them
▫️ Extremely fun
Ready for you to knock them out of the park!
Parsa retweeted
16 questions that I really like to ask during interviews for machine learning candidates.
These will help you practice, but more importantly, they will help you think and find ways to improve!
Let's do this! ☕️👇























