Learning should be available and not expensive. That’s why I compiled a list of notable learning resources.
After learning linear algebra, statistics & calculus you wonder where you should go next. That’s why I created a comprehensive list on where you could go to go next. without particular order.
d2l.ai
Dive into Deep Learning is a comprehensive guide on a lot of machine learning algorithms. All made in the beloved programming language Python. This popular book has been adopted by 175 universities from 40 countries. It teaches different approaches with different frameworks such as TensorFlow & PyTorch.
Andrew ng — Machine learning
Unlike the other learning…
A message from a procrastinator to procrastinators
Create a concrete idea
You have an amazing idea, product or piece of technology. You got an image of the product in your head. Now it is time to write it down & draw it on a piece of paper. Doing this makes your goal more touchable & real. It makes it feel like it is something you can achieve even though there is a long road in front of you.
Now you have a blueprint of what you want to work towards. The next step is creating the first small steps towards your goal. Create small but helpful steps to create the first…
Unbiased by a software engineer in detail.
We all know how the big tech companies collect as much data as possible about us and how hard it is to escape their surveillance. This browser is a private browser out of the box. This is ideal for people who don’t like configuring a lot of settings, and still want to be private.
The appearance of the brave browser
Explained in details which are easy to understand
The goal of linear regression to find a relationship between features, then using this to predict the future, with the assumption of an existing linear correlation.
Exploratory data analysis
For this example, we will use the following dataset.
x = [5, 4, 3, 6, 8, 1, 9, 2, 7]
y = [10, 9, 6, 14, 14, 2, 17, 5, 13]Just by looking at the data, we could guess if there a linear trend. To make sure our assumptions are correct, we need to confirm it with a graph. Doing this will also give us a better feeling of how the data looks.
We have all seen the word predictor of our mobile keyboards and pressing on the next prediction until it creates a ridiculous story. But how do they work and how do we create one ourselves with Python & Numpy.
