Transfer learning consists in training a base network and reusing some or all of this knowledge in a related but different task.
Transfer Style allows to use the inner understanding of an already trained Convolutional Neural Network to transfer style from one picture to another.
Data augmentation is a basic technique to increase our dataset without new data. Although the technique can be applied in a variety of domains, it’s very commonly used in Computer Vision, and this will be the focus of the post.
This post will focus on a class of metaheuristics known as Swarm Intelligence. The most amazing feature of these algorithms is their ability to solve complex problems by a set of cooperative agents posing very simple intelligence.
This post aims to show how to build an on-premise Mesos architecture to handle a disaster scenario when an entire Data Center is not available, covering also some framework strategies for zero data loss.
Correlation is very often used within the initial exploratory stage when given a dataset, because of its ability to comb through pairs of variables and swiftly summarize whether they appear to be related or not.