Objective
To give an introductory overview about datascience using a hands-on example of building a spam filter from scratch. This workshop is target to the audience who have programming skills and interested to dabble into machine learning/data sciences
After completion of this workshop you will —
- Know what is machine learning algorithm and how it is related to "learning" (http://en.wikipedia.org/wiki/Learning) in general.
- Distinguish between rule based systems and ML based systems.
- Understand how and when to apply machine learning algorithms
- Understand the basic concepts of natural language processing — the science of making a computer understand human languages
- Complete your first Machine Learning project — A spam filter!
- Pointers on how to explore the ML domain further.
Description
In the workshop, we will go through
- Basics of machine learning, classification and statistical modeling
- overview of nltk, a text processing library
- Building a text spam filter from scratch, using python.
- Improving the algorithm
Requirements
Basics of python, programming.
Laptop (preferably Ubuntu/Linux flavor) with python 2.7 installed.
Speaker bio
I am current work with Qyuki Digital Media, where I work on the in-house analytics platform and algorithms.
I have been working in text/data analytics field for last 5 year. Python is my preferred language, to implement machine learning algorithms, because of its rich library ecosystem.
1
▼
Can you please list past speaking experience at any conferences and usergroup meetings? Please post links to slides of those talks if available.
1
▼
@Anand, I only have spoken in in-house events before. Slides are difficult to upload without permission, due to the mention of closed source architecture.
1
▼
I would request you to provide a bit more detail about what the audience would be able to achieve/do from the discussions arising from your talk.
1
▼
@Sankarshan, I have updated the objective to include what the audience will be able to achieve from the talk.