Deep Learning with Keras and Tensorflow
Shagun Sodhani (~shagunsodhani) |
TensorFlow is an open-source software library for Machine Intelligence.
Keras is a high-level neural networks API which runs on top of either TensorFlow, CNTK or Theano.
In this talk, I would cover the following aspects:
- A little background to Deep Learning, Keras and TensorFlow
- How to create Tensorflow models using Keras
- Language Modelling example where we build the model using Keras and analyse using TensorBoard
- Tips, gotachs, do's and don'ts
Attendees should have a basic idea of machine learning and be comfortable with Python
The code and presentation (along with detailed explanation) would be available here.
I am a Machine Learning developer working with the Data Science and Analytics team at Adobe Systems. I have been working in Deep Learning for the past 1 year and Python for past 5 years. I recently did a Question Answer session on Deep Learning with Commonlounge Community. I have also been a teaching assistant for the 3-course series titled Data Science and Engineering with Spark XSeries, created in partnership with professors from University of California, Berkeley, University of California, Los Angeles and Databricks and offered on the edX platform.
I have good experience of public speaking and have previously given talks at: