ML & AI edition

Agenda:

Talk-1:
Eliza to Sophia - An introduction to Affective computing
by Rohan Banerjee

Participants will be able to appreciate the power and scope of affective computing. I will walk them through the model which detects emotions in real time. After the talk, the audience will have a deep understanding on what Convolutional Neural Network (CNN) is, how to build a CNN algorithm, and implement facial emotion recognition. I will also explain the architecture of a CNN and walk them through libraries like keras to give them an insight into their power. They will learn about various ways to increase the accuracy of a model using data augmentation and hyper-parameter tuning

Talk-2:
An introduction to generative adversarial networks
by Sadhana Srinivasan

GANs are a new framework for estimating generative networks proposed by Ian Goodfellow in 2014. Since then they have been well explored and have been applied in diverse problems such as super resolution and transferring manga to real images. I would like to introduce GANs and try to walk people through the first ever GAN that was trained.

Networking break

Talk-3:
Building a Flappybird playing AI in Javascript
by Kuldeep Anand

Talk-4:
One-Shot Learning
by Karthik Prabhu (github.com/karthik-13)

One-shot learning is an object categorization problem in Computer Vision commonly used in image search. Unlike traditional Machine Learning algorithms that use very large datasets to learn, One-shot learning relies on one or very few training images to learn information.

Talk-5:
Making AI Development Easy
by Anshuman Pandey (https://twitter.com/anshuman_01_)

Using Jupyter? But can you write production level code in Jupyter.
This talk explores using the right frameworks, cloud platform and packages to write code that can be used and implemented to solve real business problems.