Giving Machines Perception - Tensorflow
I build distributed systems with a focus on data science, and data engineering. I'm also keen on DDD, CQRS, Event Sourcing, functional programming, and most things software engineering-y.
I suffer from MOOC abuse.
Modern hardware has enabled practical applications of neural networks. This is enabling machines to do incredible things. In this session, we will look at them, and see Google’s Tensorflow in action.
Machines are doing things today that were unthinkable even a few years ago. From computer vision, to understanding human conversation, to translating text, or even generating art – they’re encroaching on domains previously thought to be strictly human realms. The technology behind this is actually fairly old; neural networks have been around for decades. However, modern hardware capabilities have made them technology feasible to such a degree that they can now drive cars.
TensorFlow is an open source software library for machine learning across a range of tasks, and developed by Google to meet their needs for systems capable of building and training neural networks to detect and decipher patterns and correlations, analogous to the learning and reasoning which humans use. In this session, we will take a brief look at the theory behind neural networks, and see Tensorflow in action.