Multi-pose estimation is currently a state-of-the-art deep learning approach in computer vision for detecting humans and their joints in an image. In this article, I outline briefly how you can make a funny little bobble-head GIF like the one I produced above using Lebron James’ face on top of Drake’s…

A Decision Tree is a powerful supervised learning tool in Machine Learning for splitting up your data into separate “islands” recursively (via feature splits) for the purpose of decreasing the overall weighted loss of your fit to your training set. What is commonly used in decision tree classification is the…

In this article, we will build a similar images finder by dissecting the trained weights of the image object-classifier VGG and using it to extract feature vectors from an image database to see which images are “similar” to each other. This technique is called transfer learning and requires no training…

High-level deep learning libraries such as TensorFlow, Keras, and Pytorch do a wonderful job in making the life of a deep learning practitioner easier by hiding many of the tedious inner-working details of neural networks. As great as this is for deep learning, it comes with the minor downside of…

In this article, we discuss how to reduce a double-agent Hunter-Prey problem on a (N, N) grid to a single-agent Grid World problem on a (2N-1, 2N-1) grid using relative coordinates of the hunter with respect to the prey. Although our method described here is one of many unique ways…

What is Grid World? Grid World is a 2D rectangular grid of size (Ny, Nx) with an agent starting off at one grid square and trying to move to another grid square located elsewhere. Such an environment is a natural one for applying reinforcement learning algorithms to discover optimal paths…

The multi-armed bandit problem is a classic reinforcement learning example where we are given a slot machine with n arms (bandits) with each arm having its own rigged probability distribution of success. Pulling any one of the arms gives you a stochastic reward of either R=+1 for success, or R=0…

In this article, we will explain how autoencoders can be used for finding similar images in an unlabeled image dataset. Along with this, we provide the Python implementation of an image similarity recommender system trained on steak house food images at: https://github.com/ankonzoid/artificio/tree/master/image_retrieval For more of my blogs, tutorials, and projects…