Skip to content

Latest commit

 

History

History
50 lines (24 loc) · 1.78 KB

README.md

File metadata and controls

50 lines (24 loc) · 1.78 KB

ML Session 1

This session is a first in a series of sessions that collectively form our Tensorflow Workshop.

With Tensorflow 2.0 released in alpha recently, we want to bring the community upto speed with the new version of the framework. This workshop is a step in that direction!

In the first session of the workshop, we introduced the participants to a typical ML pipeline and talked about various paradigms of learning (Supervised, Unsupervised, etc.).

We also demo-ed three basic ML algorithms for the participants to be able to see them in action and learn the math and intuition behind them. These algorithms were:

  • Linear Regression
  • K-Nearest Neighbours
  • K-means clustering

At the end of the session, we opened a Kaggle contest for the students to participate in and play around with what they learnt.

With this session, we want to make our path towards Deep Learning, motivate it in a manner that makes the community realise the importance of Deep Learning techniques and why they are necessary. Additionally, our end goal is to bring them to a point where they can explore Deep Learning on their own with Tensorflow!

Setup

Clone this repository and move into the directory.

First, we will create a virtual environment to run our code. The virtual environment is like a sandbox where you can install Python libraries without affecting your system-wide dependencies. The way to make a virtual environment is:

pip install virtualenv

virtualenv -p python3 venv

Now, activate your virtual environment using:

source venv/bin/activate

Now install all the required Python libraries using:

pip install -r requirements.txt

Now you can launch a jupyter notebook using:

venv/bin/jupyter notebook

Now have fun playing around with the code!

Kaggle contest

More details coming soon!