Deploying Machine Learning Models at the Edge
Ankit Mahato (~ankit60) |
Data is the new Oil! But, what is its use if you cannot refine (analyse) & sell (derive value) it. Big Data has pushed the frontier of analytical processing from having analytical servers to performing analytics close to Source. This workshop will introduce the new paradigm of Analytics using Python which enables deploying Machine Learning models at the Edge (close to the data capture device).
Why attend this workshop?
Model deployment is a critical part of the analytics life-cycle and this workshop will provide hands on experience along with insights and best practices to ensure seamless and robust model deployment. The audience will get a flavor of python in embedded devices through the live and interactive demonstration using Raspberry Pi.
The talk will cover the following sections:
- Evolution of analytics (Dedicated Machines -> Cloud -> Edge) - 10 mins
- The need of Edge analytics - 10 mins
- Analytics Life-cycle (ALC): Introduction, Importance of Model Deployment, Adapting ALC for Edge Analytics - 10 mins
- Model Exchange Formats (PMML, PFA, ONNX) for Deployment: Introduction & Need for Democratizing model development process - 10 mins
- Introduction to Portable Format for Analytics (PFA) - 15 mins
- Hands-on Workshop Examples - Data Pre-processing, Deployment of Clustering, Regression, Decision Tree, Neural Network - 60 mins (Models will be deployed on your laptops)
- Edge Device Introduction - Raspberry Pi - 5 mins
- Model Deployment on Edge Device (Raspberry Pi) using Python - 15 mins
- Q&A -15 mins
This workshop is not restricted to IoT devices (like Raspberry Pi) as Edge, but will also cover Model deployment techniques on your Android Smartphones as an Edge device.
Basic Python Programming
pip install git+https://github.com/animator/python3-titus.git
Install Anaconda 3.7 suite (includes jupyter & pandas) and install avro-python3 package
pip install jupyter, avro-python3, pandas
To run R codes:
- install R-Studio
- install packages: aurelius, survival
Workshop Slides (a tentative outline which will be enhanced further) - https://www.slideshare.net/secret/7Fz01KFZJka5ma
A die hard Pythonista, Ankit is an open source contributor and a former Google Summer of Code scholar under Python Software Foundation. Currently, he is developing the open source Portable Format for Analytics (PFA) implementation - Titus on Python 3 and volunteering for the Raspberry Pi Foundation.
Ankit has 5+ 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 Edge Analytics and has presented his work in the Data Science Congress 2018, 5th IIMA International Conference on Advanced Data Analysis, Business Analytics and Intelligence 2017 and SciPy India 2017. He is also an active contributor to the Indian Python Community and has conducted workshops in PyCon India 2017 and Scipy India 2017 & 2018.