DeepLearning Demystified

Photo by Greg Rakozy on Unsplash

My father always say

“To explain even most complex thing in simple,easy way is Knowledge.”

In this post , I will be sharing my views on myths that beginners come across while indulging in Deep Learning.

Deep Learning is not complete AI.It is a subfield of Machine Learning which based on biological aspect of brain to achieve or perform a task.


“A little boy holding a book with a surprised expression on his face” by Ben White on Unsplash

We don’t need to have Ph.D in order to work on it .Although it is complete necessary to have some knowledge on differentiation,mean,standard deviation,distribution ,etc.

  1. There is difference b/w the terms AI(Artificial Intelligence),ML(Machine learning),DL(Deep learning).Don’t be confuse as some time people use them interchangeable.
  2. I will encourage you to have some command on numpy and matplotlib or any visuilzation library ,it will be useful if learning from scratch or want to understand things from core.
  3. Basics will always remain important no matter what others say.Ex.- back-propagation,gradient descent,optimization technique and weight-bias trade off. These are concepts which we you need to have clear understanding.
  4. Using Library like Tensorflow,Keras,Pytorch is good but also try to read their documentation.It contain useful information
  5. Don’t be at Rush to execute each model or simply use any code,take your time ,understand and ask from others on opinion on your work.
  6. Try to read Research paper and try to visualize its perception,slowly but regular reading and you will be able to understand it.
  7. We don’t need to train model from scratch, we can train them on top of pre-trained model also.
Photo by Morvanic Lee on Unsplash

Reading Research paper will be advantageous if you want Deep Learning as carrer path. Ex- you can also go through

Two Minute Paper ( Károly Zsolnai-Fehér)from Youtube

Amazing Work

8.Any Deep learning Model follows these steps:

Load data

Preprocess data

Create Model

Update Parameter


Evaluate and check accuracy

9.There are many good resources to learn and understand about Deep learning.Ex-

CS231n of Standford, from Andrew Ng, from Jeremy Howard.

Note-All courses are good,free and provide platform for like minded peoples to interact.

Source: Deep Learning on Medium