This course has been updated many times to keep it fresh and to add more than the basic with:
β’ Problem Framing
β’ Data Prep
β’ Clustering
β’ Recommendation
β’ Test and Debug
β’ GAN
3/7π§΅
2 - Prepare an environment to learn and try ideas easily
This could be your own PC but that gives extra work:
β’ installing and keeping libs up to date
β’ updating drivers
There's also the cost of having a good HW (w/ GPU) and lot's of space (ML might need GBs of data)
Which programming language do I need to know to start with Machine Learning?
π π€π§
[1 quickβ‘οΈ min]
1/5π§΅
The easy answer is: If you know how to code well, that's all you need to start learning ML!
TensorFlow for example enables you to use ML in many languages like C++, Java, Kotlin, Swift, Objective C, JavaScript, Go, Julia, Scala, Ruby, C# and many others
Butβ¦π
2/5π§΅
The more realistic answer: Pythonπ
Most of the ML samples, tutorials and content in general you'll see is written in Python
Understanding the basics of the language will definitely make your life MUCH easier
If you use the internet, there's a big chance that you already experienced the results of a Machine Learning Recommendation System
They, given a list of possibilities and your past choices, suggest items of the list that might interest you
Lets understand more about them
1/6π§΅
Recommender Systems have a huge Impact:
β’ 40% of app install on Google Play π€βοΈ
β’ 60% of watch time on YouTube πΆπ±
β’ 35% on purchases on Amazon πΈ
β’ 75% of movie watches on Netflix πΏ
2/6π§΅
Recommender Systems are very hard to train/evaluate/deploy:
β’ Lots of features! π°π±
β’ Optimize to multiple objectives βοΈ
β’ Metrics can be misleading π€
β’ Require lots of resources to be served π°πΈ
Following up from my previous thread, let's continue taking a look at some additional itertools methods
Some of them, as you will see, have very similar built-in versions but the key here is: itertools works on iterables and generators that are lazy evaluated collections
1/14π§΅
One example is the method islice. It does slicing but for iterables (potentially endless collections). The main difference is that it doesn't accept negative indexes like regular slicing.