Immortal333

Location: India

Remote: Yes

Willing to relocate: Probably yes

Technologies: Python, Flask, PyTorch, Spacy, C

Areas: NLP, CV, Optimization

Résumé/CV: https://read.cv/dipkumar/

Email: [email protected]

Why hire Dip: - Worked as machine learning engineer + research engineer + backend engineer.

- single handedly deployed multiple ML system in production

- I believe creating baseline first and improving from it instead of going with biggest weapon.

- fast learner (worked on various project ranging from stitching photos to speech intent detection to solving NP-hard problems)

Why not to hire Dip:

- Need Research Scientist instead of MLE or Research Engineer

- Need senior (experienced) backend engineer

>>> The cheapest automatic Tissot is around 700USD.

Is the engineering/logistics behind Mechanical watches really costlier than Oneplus phones ?

Chaining has its own benefits. But I think this doesn't fit the definition of "Pythonic". Again, "Pythonic" is highly debatable. But, You can always break down big chain of operations, into smaller chain using good variable naming in-between.

Many operations are implemented as iterator in python on list, like filter, groupby. Looking at your code, its looks like you're not doing lazy computation. (Correct me if I wrong). This could be huge performance impact, depending upon use case of list.

Yes, Exactly same as you described.

Yes, FAISS not FLANN. my mistake. cann't correct it now. because edit time is gone.

This is great. This is already better that FLANN (by facebook), Annoy (by spotify). https://github.com/erikbern/ann-benchmarks#evaluated

Still, We are very far away from creating reverse video search engine. Also, Most of these techniques are in-memory not on disk.

I am really interested in making reverse video search engine.

Shameless plug. I did similar in my OS course. But, in C. Github: https://github.com/immortal3/EbFS

Warning: Terribly written. many hacks.

I've never worked at a FAANG, too. But main reason I want to work at one is that ability to do project at a scale which is not possible anywhere. Few project are no use for small companies/startups.

For example: Optimizing compile time (no need to invest for extra 1 minute speed up), working on high quality labelled data (i came from ML background, this is not possible in most of startups), analytics on data (questionable ethically), working on Ad platforms, working on large scale system.

In the last, Imagine, even making simple changes have bigger impact on real world.

It might be possible that these people have tried on more platforms (Face recognition APIs) but only reported those where they got good accuracy in terms of defeating system.

I personally would like to see tests done on facebook by uploading these images and checking if it can recognize it.

This is tested on existing models/Face Recognition API which means locked pre-trained models. So, They might have learned way to add pixels such that model outputs very different embedding. This is know issue in deep learning [0][1][2].

I believe, Model trained on cloaked images would defeat its purpose and make this technique useless.

[0] Su, Jiawei, Danilo Vasconcellos Vargas, and Kouichi Sakurai. "One pixel attack for fooling deep neural networks." IEEE Transactions on Evolutionary Computation 23.5 (2019): 828-841.

[1] Guo, Chuan, et al. "Countering adversarial images using input transformations." arXiv preprint arXiv:1711.00117 (2017).

[2] Liu, Yanpei, et al. "Delving into transferable adversarial examples and black-box attacks." arXiv preprint arXiv:1611.02770 (2016).

Hint for solving: Esoteric programming language

Location: Ahmedabad, India

Remote: Yes

Willing to relocate: Yes

Technologies/Skills: Machine Learning, Deep Learning, Computer Vision, Python, Pytorch, Flask

Résumé/CV and Email : available on Personal website

Personal Website: pi pi pi pi pi pi pi pi pi pi pika pipi pi pipi pi pi pi pipi pi pi pi pi pi pi pi pipi pi pi pi pi pi pi pi pi pi pi pichu pichu pichu pichu ka chu pipi pipi pipi pipi pi pi pi pi pikachu pi pi pi pi pi pi pi pi pi pi pi pi pikachu pikachu ka ka ka ka pikachu pichu ka ka ka ka ka ka ka ka ka ka ka ka pikachu ka ka ka ka ka ka ka ka ka ka ka pikachu pikachu pipi ka ka ka ka ka ka ka pikachu pi pi pi pi pikachu pikachu pi pi pikachu pi pi pi pikachu pi pi pikachu ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka pikachu pi pi pi pi pi pi pi pi pi pi pi pikachu pichu pi pi pi pi pikachu ka ka ka ka ka pikachu pipi ka ka ka ka ka pikachu pi pi pikachu pi pi pi pi pi pi pi pi pi pi pi pikachu ka ka ka ka ka ka ka ka ka ka ka ka pikachu pi pi pi pi pi pi pi pi pi pi pi pi pi pikachu ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka ka pikachu pichu pikachu pipi pi pi pi pi pi pi pi pikachu pi pi pi pi pi pi pikachu pichu pi pikachu

After, reading your comment. I cross checked result and found out that 3 is most optimal size. I even ran fib(40) on it. with size 2, There are many misses but after 3 and on wards misses are constant(if fib(40), then misses are only 40 which emulates DP approach of O(N)).

Why 3 is optimal, because of how recursion and LRU work. I wish i can explain it using animation.

You can play with it. https://repl.it/repls/NocturnalIroncladBytecode#main.py

Thanks for similar articles. I am aware of similar articles and that's why I have kept it short and simple. I will add these as references, later.

I have enjoyed reading Python Tricks[0] book by Dan bader (author of https://dbader.org/blog/python-memoization ). It's awesome. Might be outdated but I still recommend it to any body who has just started learning python.

[0] https://realpython.com/products/python-tricks-book/

Yes, I have mentioned DP in my article as just reference. The Purpose of article was to show that how easy it is to implement caching in python using lru_cache decorator which is in std lib. So, We don't have to install any 3rd party lib.

Author here. Sorry, If it feels misleading. I have no intention to mislead anybody. If you can suggest alternative title, I am happy to change title.

When I looked at the features of hey email ( https://hey.com/how-it-works/ , https://hey.com/features/ ), I recognized similar features and ideas already present in many SMS organizers. For example, SMS organizer from Microsoft: https://play.google.com/store/apps/details?id=com.microsoft....

I was able to get the second part of the statement. but I haven't seen the use of "in limit" in a statement like this.

Yes, the universal approximation is a strong claim. NN has been proven to have universal approximation theoretically.

"We show that this architecture gives rise to universal learning capabilities in the limit, with effective model capacity increasing as a function of network size in a manner comparable with deep ReLU networks."

What exactly this statement means?

Yes, English is not my native language. I think I can tell someone to proofread it and correct my mistakes. Thanks for your feedback.

At glance, It looks like ongoing research of Multi-Task and Meta-Learning will be discussed. Some new tricks on the architecture of NN, Few new methods to train, and some theoretical setting of the area. I will be looking forward to seeing whole series. Maybe share some notes or summary of videos.

Machine Learning Engineer

Location: Ahmedabad, India

Remote: Yes

Willing to relocate: Yes (Note: need work visa)

Technologies.Skills: Machine Learning, Deep Learning, Computer Vision, Python, Pytorch

Résumé/CV: https://github.com/immortal3/immortal3.github.io/raw/master/...

Personal Website: https://immortal3.github.io/

Email: ( Available in the resume )

-----------------

Also, willing to accept SWE or Backend Engineer job.