Neural Networks are used
all around us: they index photos into categories, translate text,
suggest replies for emails, and beat the best games. Many people are
eager to apply this knowledge to their own data, but many fail to
achieve the results they expect.
In this course, we’ll
start by building a simple flower recognition program, making you feel
comfortable with Tensorflow, and it will teach you several important
concepts in Neural Networks. Next, you’ll start working with
high-dimensional uses to predict one output: 1275 molecular features you
can use to predict the atomization energy of an atom. The next program
we’ll create is a handwritten number recognition system trained on the
famous MNIST dataset. We’ll work our way up from a simple multilayer
perceptron to a state of the art Deep Convolutional Neural Network.
In the final program,
estimate what a celebrity looks like, checking for new pictures to see
whether a celebrity is attractive, wears a hat, has lipstick on, and
many more properties that are difficult to estimate with "traditional"
computer vision techniques.
After the course, you’ll
not only be able to build a Neural Network for your own dataset, you’ll
also be able to reason which techniques will improve your Neural
Network.
About The Author
Roland Meertens develops smart computer-vision algorithms for
self-driving vehicles at AID. Previously he worked on deep learning
approaches for natural language processing (NLP) problems, social
robotics, and computer vision for drones.
During his studies in Artificial Intelligence at Radboud University,
he specialized in cognitive artificial intelligence and brain-computer
interfacing.
Make sure you follow him on Twitter: rolandmeertens, and visit his blog pinchofintelligence.com.
