In this series of posts, I will pick a source for Deep Learning and try to share my understanding and learnings on the topic. I want to treat this as my notes from these lessons. My notes tend to be very rough, in an attempt to keep a semblance of formality to them I am putting them out in public.
Machine Learning is primarily all about extracting information from data. Unlike simple situations in life data in Machine Learning comes in larger quantities. The most common form of this “large quantity” is a list of numbers. Mathematically, we would like to apply some abstraction and perform operations on them. Vectors are a good abstraction for such cases, a collection of such vectors can be represented by Matrices. Now Tensors are a generalized form of matrices allowing data to be represented along several axes.
Linear Algebra helps us understand the rules of simple operations on such a collection of numbers. In this post, I will only list the items or topics from Linear Algebra that we will need to apply Deep Learning in a practical manner.
Here’s the list, each of which we will cover in detail in future posts.
- Reduction of Tensors
- Non-Reduction Operations: Sum
- Dot Products
- Matrix-Vector Products
- Multiplication of Matrices
- Norms - L2, Frobenius
As mentioned earlier, we will cover some or all of these topics in a bit more detail in separate tiny bite sized posts. Until then, happy whatever!
If you like topics such as this then please consider subscribing to my podcast. I talk to some of the stalwarts in tech and ask them what their favorite productivity hacks are:
Available on iTunes Podcast
Visit Void Star Podcast’s page on iTunes Podcast Portal. Please Click ‘Subscribe’, leave a comment.
Available on Google Play Music
Visit Void Star Podcast’s page on Google Play Music. Please Click ‘Subscribe’ and leave a comment.
Available on Stitcher
Visit Void Star Podcast’s page on Sticher. Please Click ‘Subscribe’ and leave a comment.
Your app not listed here? Not an issue..
You should be able to search for ‘VoidStar Podcast’ on your favorite app.
Most apps use one of the above sources for listing podcasts. This was tested on
Podcast Addict (where you can also specify the search engine) and
RatPoison on Android.