Just because computers can perform calculations quickly doesn’t mean that they are perfect.
Unlike traditional software development, as you progress further in data science and AI, you will encounter more and more advanced mathematics. Given the sad state of how math is taught in schools today (at least in the US), learning math quickly can dramatically impact the quality of your life and your career options.
Fortunately, Siraj Raval has got our back and, in this video, he offers up tips on how to learn math more quickly.
Here’s great explainer video on the math behind quantum computers.
Humans have been trying to quantify consciousness for at least as long as there have been written records and, likely, this search for understanding predates written records.
This is an area where recent advances in math and AI research starts shedding new light on an old topic. In this TEDx talk, Max Tegmark explores the notion of consciousness as an emergent mathematical pattern.
Siraj Raval explains the importance of math to machine learning.
Since I started doing Data Science a few years ago, I have used more advanced mathematics than I ever thought I would have. And, as I take the DeepLearning.ai classes, that use of mathematics has accelerated.
Given that the math side of Data Science and AI is not going away any time soon, it’s probably best to get good at it.
Fortunately, for all of us Siraj Raval explains how to read math equations in a way that only he can: quickly and awesomely.
Not content to school the world on the wonderful world of AI, Siraj Raval brings his unique teaching style to bare on the mathematics behind cryptography (and, by association, cryptocurrencies).
From the video description:
The math behind cryptography is immensely fascinating, I could spend all day studying it! We’re going to go over some fundamental cryptographic concepts like hashing, zero knowledge proofs, and my favorite ‘ZK-Snarks’. This is quite an in-depth video, i had to pick and choose the topics i wanted to dive into more. There is so, so much i could talk about. Each of these topics could deserve their own course. Cryptography is going to be paramount to building future decentralized Artificial Intelligence systems that we can both control and protect from attackers.
From time to time, the term “non-Euclidian geometry” comes up in the context of creating models for AI systems.
Here’s a great explainer of what non-Euclidian geometry.
It’s not quite explaining a support vector machine, but it’s an interesting refresher on some basic mathematical concepts.
In this series of videos by the one and only Siraj Raval, learn the essential mathematical building blocks of AI and Machine Learning in a fun and engaging way.