Deep Learning 101

Note: This is a nominally charged workshop at INR 500 with limited capacity of 50 participants. You need to buy the ticket at https://boxoffice.hasgeek.com/narrativeviz/dl101 to attend the session.

“All knowledge is connected to all other knowledge. The fun is in making the connections.” — Arthur Aufderheide

The objective for the Deep Learning 101 (introduction to deep learning) is to ensure that the participants have enough theory and practical concepts of building a deep learning solution.Post the session, all the participants would be familiar with many of the key concepts and would be able to build simple deep learning models.

Key Concepts

•Theory: DL Motivation, Back-propagation, Activation

• Paradigms: Supervised Models:

• Architecture, Pre-trained Models (Transfer Learning)

• Methods: Perceptron, Convolution, Pooling, Dropouts

• Process: Setup, Encoding, Training, Serving

• Tools: python-data-stack, keras

Approach

This would be a half-day instructor-led hands-on workshop to learn and implement an end-to-end deep learning model for classification.

Session Breakdown

Deep Learning (DL) Theory

• What is deep learning?

• Use cases in computer vision and natural language processing

• Overview of the building blocks - Neurons, Activation functions, Back propagation algorithm, Stochastic gradient descent

• Multi Layer Perceptron

• Convolution Neural Network

• Transfer learning

Hands-on

• Introduction to keras

• Overview of the cloud setup

• Introduction to the problem

• Build first model - MLP

• Build second model - CNN

• Build third model - transfer learning

Resources

The material for the workshop is hosted on github:

• For Image: https://github.com/rouseguy/DeepLearning-Image

• For NLP: https://github.com/rouseguy/DeepLearning-NLP

This is from the popular workshop series by the speakers on deep learning.

Target Audience

Anyone interested in understanding ML/AI/DL

Pre-requisites

Exposure to basic programming paradigms is ideal. It is preferred that participants brush up a bit of Python before attending the session.

Software Requirements

We will be using a cloud service. No software setup needed. Please get a laptop for the workshop.

Facilitators’ Profile

Amit Kapoor teaches the craft of telling visual stories with data. He conducts workshops and trainings on Data Science in Python and R, as well as on Data Visualisation topics. His background is in strategy consulting having worked with AT Kearney in India, then with Booz & Company in Europe and more recently for startups in Bangalore. He did his B.Tech in Mechanical Engineering from IIT, Delhi and PGDM (MBA) from IIM, Ahmedabad. You can find more about him at http://amitkaps.com/ and tweet him at @amitkaps (https://twitter.com/amitkaps).

Bargava Subramanian is a Data Scientist and helps early-stage startups setup their data science practice. He has 14 years of experience delivering business analytics solutions to Investment Banks, Entertainment Studios and High-Tech companies. He has given talks and conducted workshops on Data Science, Machine Learning, Deep Learning and Optimization in Python and R. He has a Masters in Statistics from University of Maryland, College Park, USA. He is an ardent NBA fan. You can find more about him at http://bargava.com/ and tweet him at @bargava (https://twitter.com/bargava).

Parking at Location

The closest landmark to the location is Forum Mall in Koramangla. There is very limited underground parking for cars at the location. So if you are coming by car, you best bet would be paid parking at the Forum Mall. Bikes should be fine, as there is parking on one side of the wall of the building. It is best to use public transport or Uber/Ola to come to the location.