Deep Learning is a machine learning approach where successive layers of representations are used to train models. Deep Learning has recently become popular because of its ability to study images, text, audio, or video data.
Keras is an open-source deep learning Python library that has been developed to facilitate rapid experimentation with neural networks. Keras is used at Google, Uber, Netflix, CERN and hundreds of other AI-focused companies.
Our two guest speakers for this meetup are from Google and IVADO Labs.
*** Topic 1: Introduction to Keras
This talk introduces Keras from core concepts to advanced experimentation. Keras is an API for specifying and training deep learning models in TensorFlow, CNTK, MXNet, theano and others frameworks. It is used extensively in industry and academia by data scientists, engineers, researchers and students. It allows coders to quickly develop and experiment with powerful deep learning algorithms. Keras has a very large online community with tons of examples and reference architectures.
*** Topic 2: A demo of Google Cloud ML Engine for Deep Learning
In order to demonstrate how to leverage the power of Google ML-Engine to easily train a deep learning classification model, we will do a hands-on demonstration of a full workflow to train a simple classification deep learning model:
• Jupyter Notebooks to prepare the dataset, generate predictions and analyze results
• TensorBoard to manage the trainings
• Google ML-Engine to run the model locally or on the cloud with hyperparameter research
NEW LOCATION: Notman House, 51 Sherbrooke West (notman.org)
6:30 - 6:45 PM: News and Introduction
6:45 – 7:30 PM: Introduction to Keras
7:30 - 8:15 PM: A demo of Google Cloud ML Engine for Deep Learning
8:15 - 8:30 PM: Wrap-up
(This February meetup is sponsored by Ivado Labs)