Description:

"Data is the new Oil!"

But, what is the benefit of this oil if you cannot refine (analyse) and sell/use (derive value) it. Big Data has pushed the frontier of analytical processing to gather more actionable insights in the past decade from having separate analytical servers to performing analytics close to the Data Lake/Cloud. A new paradigm of FOG computing has recently emerged which enables analyzing data at the Edge (close to the data capture device). This talk will focus on Edge Analytics enabled by Python & Raspberry Pi.

Why attend this session?

This session will provide a first hand look into the paradigm of FOG computing and Edge analytics. Model deployment is a critical part of the analytics life-cycle and this talk will provide insights and best practices to ensure seamless and robust model deployment. Also, the audience will get a flavor of python in embedded devices through the live and interactive demonstration using Raspberry Pi.

Content

The talk will cover the following sections:

• Evolution of analytics (Dedicated Machines -> Cloud -> Edge)
• The need of Edge analytics
• Analytics Life-cycle (ALC): Introduction, Importance of Model Deployment, Adapting ALC for Edge Analytics
• Model Exchange Formats (PFA, ONNX) for Deployment: Introduction & Need for Democratizing model development process
• Edge Device Introduction - Raspberry Pi
• Introduction to Portable Format for Analytics (PFA)
• Model Deployment on Edge Device (Raspberry Pi) using open source PFA engine implemented in Python
• Hands-on Application Use Cases - Deployment of Clustering, Regression, Decision Tree, Neural Network/ Deep Learning Models

Prerequisites:

• Python 2.7.x
• titus python package (pip install titus)

Content URLs:

TBD

Speaker Info:

A die hard Pythonista, Ankit is a full time open source contributor and a former Google Summer of Code 2013 scholar under Python Software Foundation. Currently, he is developing the open source Portable Format for Analytics (PFA) implementation - Titus on Python 3.

Ankit has 4 years of industrial experience in machine learning, quantitative modelling, data analytics and visualization. Over the years, he has developed an expertise in handling the entire data analytics pipeline comprising – ingestion, exploration, transformation, modeling and deployment. He is a polyglot programmer with an extensive knowledge of algorithms, statistics and parallel programming. He has shipped multiple releases of DB Lytix, a comprehensive library of over 800 mathematical and statistical functions used widely in data mining, machine learning and analytics applications, including “big data analytics”.

An IIT Kanpur alumnus, Ankit is also an active researcher with publications in international journal and conferences. He is actively working in the domain of IoT Analytics and has recently presented his work:

• "Discovering Knowledge from Smart Meter Data using Competitive Learning Methods" in the Data Science Congress 2018.
• “In-database Analytics in the Age of Smart Meters” in the 5th IIMA International Conference on Advanced Data Analysis, Business Analytics and Intelligence, 2017.
• “Smart Meter Data Analytics using Orange” in Scipy India 2017, Mumbai.

Ankit is an active contributor to the Indian Python Community and has conducted the following workshops in PyCon India and Scipy India:

• Scientific Computing using Orange in SciPy India 2017, Mumbai.
• Making Machine Learning Fruitful and Fun using Orange in PyCon India 2017, New Delhi.

Speaker Links:

LinkedIn

Youtube channel

Github