Tutorial: Learning to teach machines with Keras

Abstract

This workshop is a one-stop onboarding for the people who have not yet caught upon the Machine learning trend. This workshop aims to get people acquainted with the knowledge and working of the key algorithm behind the machine learning paradigm.

Description

A complete hands-on session in Keras that would encompass on the following topics: - ## The basics This section of the workshop will let give a deep dive in the fundamental concept of the basic architecture that cemented the way for the deep learning model. This section of the workshop will contain the most amount of theoretical concepts. Creation of Linear Regression, Logistic Regression and Neural Nets from scratch and then using Keras. - ## Advanced This is the second part of the workshop. This part deals with the formation of advanced style of neural nets, these nets are specialized to carry out a certain type of task and are developed with a genre-specific approach. This section would be a more of hands-on session with Keras. This section would be further divided into 2 parts: - Image This section would be majorly concerning with convolution neural networks and their degenerates. - Text This section will cover some well-recognised task related to text. This will majorly introduce attendeees to the algoriths like RNNs, LSTMs and GRUs.

Slides

http://bit.ly/pycontwkeras

Lecturer

Prakhar Srivastava

Greetings to everyone,

I'm Prakhar Srivastava, researcher, open source lover, and a student. I have worked on Deep learning models for 3 years now and mentor the deeplearning.ai course on Coursera. I've researched with India's leading research college, IIIT Delhi (http://midas.iiitd.edu.in/team/prakhar.html). I've worked as a student developer in GSoC'18 under OpenAstronomy and as a team leader at Stanford Scholar initiative. I've hosted complete lecture sessions on Deep learning in my college under IEEE. I'm currently working as a Machine learning and research intern at SocialCops, one of India's leading startups.