gaspersic/freeCodeCamp
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Corrected some typos (#30176)

Browse Source
This commit is contained in:
Ashwin Aishvarya Vardhan
2019-04-07 14:20:45 +05:30
committed by The Coding Aviator
parent 15181b616c
commit db7649a0b0
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
guide/english/machine-learning/deep-learning/index.md
View File

@ -2,14 +2,14 @@
title: Deep Learning
---
## Deep Learning
Deep Learning refers to a technique in Machine Learning where you have a lots of artificial neural networks stacked together in some architecture.
Deep Learning refers to a technique in Machine Learning where you have a lot of artificial neural networks stacked together in some architecture.
To the uninitiated, an artificial neuron is basically a mathematical function of some sort. And neural nets are neurons connected to each other. So in deep learning, you have lots of mathematical functions stacked on top (or on the side) of each other in some architecture. Each of the mathematical functions may have its own parameters (for an instance, an equation of a line `y = mx + c` has 2 parameters `m` and `c`) which need to be learned (during training). Once learned for a given task (say for classifying cats and dogs), this stack of mathematical functions (neurons) is ready to do its work of classifying images of cats and dogs.
To the uninitiated, an artificial neuron is basically a mathematical function of some sort. And neural nets are neurons connected to each other. So in deep learning, you have lots of mathematical functions stacked on top (or on the side) of each other in some architecture. Each of the mathematical functions may have its own parameters (for an instance, an equation of a line `y = mx + c` has 2 parameters `m` and `c`) which need to be learnt (during training). Once learnt for a given task (say for classifying cats and dogs), this stack of mathematical functions (neurons) is ready to do its work of classifying images of cats and dogs.
![Cat or a dog?](https://image.slidesharecdn.com/deeplearningfromanoviceperspective-150811155203-lva1-app6891/95/deep-learning-from-a-novice-perspective-3-638.jpg?cb=1439308391)
### Why is it a big deal?
Coming up with set of rules manually for some of the tasks can very tricky (though theoretically possible). For instance, if you try to write a manual set of rules in order to classify an image (basically bunch of pixel values) of whether it belongs to a cat or dog, you'll see why it is tricky. Add to that the fact that dogs and cats come in variety of shapes, sizes and colors, and, not to mention, the images can have different backgrounds. You can quickly understand why coding such a simple problem can be problematic.
Coming up with a set of rules manually for some of the tasks can be very tricky (though theoretically possible). For instance, if you try to write a manual set of rules in order to classify an image (basically bunch of pixel values) of whether it belongs to a cat or dog, you'll see why it is tricky. Add to that the fact that dogs and cats come in variety of shapes, sizes and colors, and, not to mention, the images can have different backgrounds. You can quickly understand why coding such a simple problem can be problematic.
Deep Learning helps tackle this problem of figuring out the set of rules that can classify an image as that of a cat or a dog, automatically! All it needs is bunch of images that are already correctly classified as that of a cat or a dog and it'll be able to learn the required set of rules. Magic!