Developing a Webcam Arcade Controller using Deep Learning by TensorFlow & Keras - Video & Slides
Following our successful Fullstack event, we are happy to share the video & slides with you.
We will introduce Deep Learning, demo a DL model in action, introduce an architecture for training and use of such model in a production environment, and show some critical sections of the code.
Session #1 by Haim Cohen, Big Data Architect & Shai Tal, Data Scientist and Machine Learning Engineer
- Demo - Control video game using Deep Learning
We will demo an application which makes use of deep learning to control a video game through webcam and head gestures.
- Deep Learning Overview
We will briefly discuss the practical benefits of machine learning over programming, and the benefits of deep learning over classical machine learning for building visualization and NLP models.
- Deep Learning API’s & Architecture
We will Introduce TensorFlow & Keras through code examples, go through essential parts of the demo application and talk about the architecture of this application and other Deep Learning based systems.
Session #2 - DevOps Concerns for Deep Learning Systems - by Haggai Philip Zagury, DevOps Architect
Data science demands for computing and environment are ever growing, pipelines are getting more complex than ever, in research and production. Cloud resourced offer a solid solutions for those dynamic needs, alongside new budget and management challenges.
We will review and demonstrate various strategies for creating a budget friendly, provider and environment agnostic data science pipelines using cutting edge tools such as kubernetes, kubeflow & many moreInvite us for a bonus lecture to your team