Important paper from Google on large batch optimization. They do impressively careful experiments measuring # iterations needed to achieve target validation error at various batch sizes. The main "surprise" is the lack of surprises. [thread]

https://t.co/7QIx5CFdfJ

1/🧵 Good #DataScience advice that breaks pretty much every rule you learned in class... a thread. (+full blog post linked)

English version: https://t.co/dG4l6vPFBT
Spanish version: https://t.co/gFAjPQ5clS

#AI #MachineLearning #Statistics #RStats

2/🧵 Allow your approach to be sloppy at first and burn some of your initial time, energy, and data on informing a good direction later. That's right, you're supposed to start sloppily ON PURPOSE.

3/🧵 Have a phase where the only result you’re after is *an idea of how to design your ultimate approach better.*

4/🧵 In other words, start with a pilot phase where the objective isn't finding answers, it's finding a good approach to finding answers.

5/🧵 That means you're encouraged (ENCOURAGED!) to start with everything your stats classes told you not to do:

Which libraries do you really need to get started with Machine Learning and why?

🧵👇

First and foremost, make sure that you have nailed the fundamental concepts of Python because machine learning requires a lot of programming!

(2 / 19)

If you know these topics, then you are good to go with machine learning in Python

- Object-oriented programming in Python:Classes,Objects,Methods
- Lists & List functions
- List comprehension
- List slicing
- String formatting
- List,Dictionaries & Tuples

(3 / 19)

Now, let's understand what popular python machine learning libraries do.

We will talk about👇
- TensorFlow (+ Keras)
- PyTorch
- Pandas
- Numpy
- Matplotlib
- SciKit Learn
- Seaborn

(4 / 19)

Now let's cover the libraries that you have to learn (at least the basics) for machine learning

1. Pandas

Pandas is a python library that allows you to store and read data from spreadsheets ( .csv, .xlsv files ) in structures called Dataframes.

(5 / 19)

1 There's a chasm between an NLP technology that works well in the research lab and something that works for applications that real people use. This was eye-opening when I started my career, and every time I talk to an NLP engineer at @textio, it continues to strike me even now.

2 Research conditions are theoretical and/or idealized. A huge problem for so-called NLP or AI startups with highly credentialed academic founders is that they bring limited knowledge of what it takes to build real products outside the lab.

3 A product is ultimately a thing that people pay for - not just cool technology or user experience. But I’m not even talking about knowledge gaps in go-to-market work. I'm talking purely technical gaps: how you go from science project to performant + delightful user experience.

4 Most commoditized NLP packages solve well-understood problems in standard ways that sacrifice either precision or performance. In a research lab, this is not usually a hard trade-off; in general, no one is using what you make, so performance is less important than precision.

5 In software, when you’re making something for real people to use, these tradeoffs are a big deal. Especially if you’re asking those people to pay for what you’ve made (can’t get away from that pesky GTM thinking). They expect quality, which includes precision AND performance.

In this thread, I will tell you how to learn python for data science in 1 hour 👇 1/N

It's not possible 2/N

It's not possible 3/N

It's not possible 4/N

It's not possible 5/N