Rajeev Ratan

Rajeev Ratan is a data scientist, computer vision consultant, and researcher. He has spent the last five years working at several computer vision startups, and has created several popular online courses on OpenCV and deep learning convolutional neural networks. He holds an MSc in Artificial Intelligence from the University of Edinburgh, and has published research on using data-driven methods for Probabilistic Stochastic Modeling for Public Transport.

projects by Rajeev Ratan

Art Style Transfer with Deep Learning

2 weeks · 8-12 hours per week average · INTERMEDIATE

In this series of liveProjects, you’ll explore the capabilities of an AI algorithm to create beautiful art. You’ll create fun tools that can make photos look like paintings, and also augment image datasets for training other AI. Through hands-on machine learning projects, you’ll explore the latent space of a deep neural network, and manipulate its values to see how it affects an input image. You’ll tackle challenges such as training an image classifier, manipulating your filters to produce dreamlike images, and creating AI-generated images that look like human art.

Generate Art

1 week · 8-12 hours per week · INTERMEDIATE

In this liveProject, you’ll replicate Google’s Deep Dream algorithm to explore the artistic creations of a neural network. You’ll start by investigating the latent space of a deep neural network and how manipulating its values can affect an input image. You’ll visualize inputs that maximize your filters, and manipulate these filters to produce ‘dream-like’ hallucinations.

Using Neural Networks

1 week · 8-12 hours per week · INTERMEDIATE

In this liveProject, you’ll follow research laid out in a groundbreaking paper and work with algorithms that can take the aesthetic style of one image and apply it to another. You’ll use convolutional neural networks and transfer learning to build a simple image classifier and implement a neural style transfer. You’ll use TensorFlow and Keras to build your networks, Matplotlib and keras-vis to visualize them, and scikit-learn to analyze your results.