“Whoa!”
—Keanu Reeves (Bill & Ted’s Excellent Adventure)
We’ve mentioned the word tensor a few times, and it resides as the predominant word in TensorFlow.js, so it’s time we get to know what these structures are. This critical chapter will give you hands-on experience with the fundamental concept of managing and accelerating data, which is at the heart of teaching machines with data.
We will:
Explain the concept and terminology of tensors
Create, read, and destroy tensors
Practice concepts of structured data
Take the leap into utilizing tensors to build something useful
Take your time with this chapter if you’re new to tensors. Being comfortable with this aspect of data will help you be comfortable with machine learning altogether.
Why Tensors?We live in a world full of data, and deep down, we all know it ends in 1s and 0s. To many of us, this happens quite magically. You take a photo with your phone, and some complex binary file gets created. Then, you swipe up and down, and our binary file changes from JPG to PNG within an instant. Thousands of unknown bytes are generated and destroyed in microseconds as files resize, reformat, and, for you hip kids, filter. You can’t be mollycoddled anymore. As you venture into actually touching, feeling, and feeding data, you have to wave goodbye to ignorant bliss.
To quote the 1998 movie Blade:
“You better wake up. The world you live in is nothing but a sugarcoated topping. There is another ...
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4