Deep Learning Conf 2016

With the rapid increase in images in social media and smarter devices, there is a tremendous amount of information waiting to be tapped into. Deep learning’s design makes it a very useful tool in today’s world. Extracting the right features after necessary pre-processing of images is often challenging. This talk will cover important hacks on how to deal with images, transform and extract features for training a model.
The session will use sample test cases to show the variation in model performance based on different pre-processing techniques and model hyper-parameters. The motivation is to help data scientists find the optimal balance between trade-offs.

Outline

1. What kind of information do images hold?
2. Selection of image transformation and processing techniques
3. Hyper-parameter selection for deep nets
4. Employing Deep Learning on images to transform businesses

Requirements

N/A

Speaker bio

Hemant Jain is Data Scientist and ML enthusiast currently pursuing Computer Science and Engineering at VIT University, Vellore. He has experience in the fields of Data Mining, Computer Vision, Big Data and Machine Learning. You can know more about him @ https://in.linkedin.com/in/hemantjain1

Links

• Github: https://github.com/CoderHam