Deep Learning with PyTorch- Day 1

Original article was published on Artificial Intelligence on Medium

If you are not familiar with my week-1 plan for Lecture-1, you may want to check this out first.

The Myth of Artificial Intelligence, Machine Learning, Deep Learning and Data Science

As a beginner i was really keen on knowing what Deep Learning really is. So i went to my browser tried to read some blog post, watched some videos and it got me more tangled because the words like Artificial Intelligence, Machine Learning and Data Science were also coming up. Since these words were used simultaneously I had to dig up more and to my amusement these actually we a lot different. The picture actually sums it up.

Lets not get into ML and AI for now but lets know about Deep Learning.

Deep learning is a sub-field of machine learning with algorithms inspired by the working of the human brain. These algorithms are referred to as artificial neural networks. Examples of these neural networks include Convolutional Neural Networks that are used for image classification, Artificial Neural Networks and Recurrent Neural Networks.

Day 1 — Goal 1 (Learn Markdown styling basics.(Needed for Assignment Documentation)

So I had initially planned on learning markdown styling as it was necessary for my Jupyter notebooks to look more appealing and readable for code documentation. But I found a more efficient way on using a In-browser-Markdown editor. It is open source and to my experience I really found it user friendly.

Day 1 — Goal 2 (Learn about PyTorch (Overall what PyTorch is)

PyTorch is a Python machine learning package based on Torch, which is an open-source machine learning package based on the programming language Lua. PyTorch has two main features:

  • Tensor computation (like NumPy) with strong GPU acceleration
  • Automatic differentiation for building and training neural networks

Day 1 — Goal 3(Why PyTorch better than other Deep Learning packages for beginners?)

There are a few reason you might prefer PyTorch to other deep learning libraries:

  1. Unlike other libraries like TensorFlow where you have to first define an entire computational graph before you can run your model, PyTorch allows you to define your graph dynamically.
  2. PyTorch is also great for deep learning research and provides maximum flexibility and speed.

Day 1 — Goal 4(Review Lecture 1–01-pytorch-basics and take notes and questions)

Here I have practiced my Lecture 1 — PyTorch basic in my own way and described the codes more in the process of learning. Any feedback is appreciated.

Day 1 — Goal 5 (Complete 10% assignment)

I completed my assignment partially as well, it will be published when fully completed. It took me about 3 hours to throughly go through the learning process. I learned the difference about Artificial Intelligence ,Deep Learning and Machine Learning. I learned the basics of PyTorch and reviewed my first lecture.