In the last few years, there has been a tremendous growth in the data generated by humans, specifically in terms of images or videos. This kind of data is represented as bits and blobs, which is harder to explain to a machine. On the other hand, the applications we can build using this data is substantial – whether it be to parse scenes for a self-driving car, or build robotic machines for industry.
This workshop is meant to give you a taste of how to leverage image data and build innovative real life products, specifically using state-of-the-art techniques – aka Deep Learning.
For the workshop, we will be using PyTorch, which is an up-and-coming framework to build Deep Learning models. PyTorch is a python based library built to provide flexibility as a deep learning development platform. The workflow of PyTorch is as close as you can get to python’s scientific computing library – numpy. Since its release in the start of January 2016, many researchers and Deep Learning practitioners have adopted it as a go-to library because of its ease of use for building novel and even extremely complex neural network architectures.
Phani Srikanth (a.k.a binga) works with the data science team at Reliance Jio where he overlooks all things related to data. From Product Analytics that help improve the product by collaborating with several teams to building Machine Learning solutions, he’s a part of JioMoney’s data initiatives. Prior to joining Jio, he worked as a Data Scientist at Housing.com. He has also been an active member on Kaggle and is among the top-10 members on AV’s leaderboard.
Supreeth (a.k.a ‘ziron’) is currently working as a Data Scientist in the lending business at Ola, solving machine learning problems for the organisation. Previously, he worked on various problems across banking industry with the Innovation team at Society Generale GSC. Apart from work, he is an active participant and won several competitions including #2 in AV Datafest 2017