Keras, Deep Learning Made Easy
Thursday, September 21, 2017 — 1:30PM - 2:30PM
Quoting from the source: Keras is a high-level neural networks library, written in Python and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. https://keras.io/#keras-deep-learning-library-for-theano-and-tensorflow The session will include an in depth analysis of how Keras improves performance over TensorFlow or Theano, the two most popular libraries for Deep Learning. Keras makes it easier to convert ideas into implementations even for beginners in the field. The session will start from covering the basics of Deep Learning, its performance enhancements, the problems it can solve. Popular projects and implementations will be discussed. An introduction into customization of Keras library and its various models will conclude the session to curate to the needs of the advanced audience. The session will be end with a summary of benefits of Keras and the urge to spread awareness about the same.
Chhavi P. Gupta, Google