Anthill Inside 2017

On theory and concepts in Machine Learning, Deep Learning and Artificial Intelligence. Formerly Deep Learning Conf.

KERAS: A Versatile Modeling Layer For Deep Learning

Submitted by Ananth Krishnamoorthy (@akrishnamoorthy) on Thursday, 27 April 2017


Technical level



Full talk



Vote on this proposal

Login to vote

Total votes:  +5


As practitioners in Deep Learning, we often want to understand emerging areas by prototyping and modeling. While there are many python libraries for deep learning, Keras stands out for it’s simplicity in modeling.

Keras is a high-level neural networks API, written in Python and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. It provides a deep learning library that (1) Allows for easy and fast prototyping (2) Supports both convolutional networks and recurrent networks, as well as combinations of the two, and (3) Runs seamlessly on CPU and GPU.

In this talk, we explore the basic elements of DL and different DL architectures using Keras. To facilitate this discussion, we take three seemingly different applications: (1) Image Recognition, (2) Control a Car (Simulation), and (3) Speech Recognition

The focus of this talk is on modelling, and that is where we shall spend the bulk of our time. We will quickly discuss the basics and then look at applications, stepping through the core Keras code visually, and do a few demos. This is NOT a workshop.


Intro to Deep Learning
What is a Deep Learning Architecture?
Keras Basics
Application 1: Image Recognition
Application 2: Control a Car
Application 3: Speech Recognition


Machine Learning practitioners, Deep learning beginners, enthusiasts

Speaker bio

Ananth Krishnamoorthy Ph.D. specializes in applying analytical techniques based on mathematical optimization, machine learning, discrete event simulation, and time series analysis, to real world business problems across various industry sectors. He has delivered several business consulting, analytical solution development, and technology implementation projects over the last 17 years.

Ananth is the co-founder of rorodata, a startup that is building a cloud based data science platform. He is also head of Hypercube Analytics, an analytics consulting company. Ananth holds a Ph.D. in Industrial Engineering and Management from Oklahoma State University




Login with Twitter or Google to leave a comment