#Artificial Intelligence

Object detection is one of the most common use cases for computer vision. There are many methods of dealing with this problem, but increasingly often, neural networks are used. To achieve high performance, deep neural ne (...)

Steve Jobs unveiled the first iPhone on January 9, 2007, which is often considered the beginning of the mobile revolution. This event opened a new area for digital content creators. However, the problem was that most CMS (...)

The first content management systems (CMSs) replaced the handcrafted HTML-based websites as early as the ‘90s of the last century. At that time, the versatile CMSs of today were not even dreamt of by the owners of these (...)

Over the past few years, the field of Computer Vision has been flooded with various Deep Learning techniques, which focus on utilizing Deep Neural Networks. While this approach often seems to be the most effective, peopl (...)

Optimization is hard. Often, all that's known about a challenge is the desired outcome, but not the way to get there. In this post, we'll look into solving non-trivial problems automatically with the use of the hyperopt (...)

Controlling the quality of large volumes of training data is a complex and time-consuming task. In this post, we'll look into the problem of using noisy data in machine learning from an unconventional perspective - by ma (...)

Calibration is important, albeit often overlooked, aspect of training machine learning classifiers. It gives insight into model uncertainty, which can be later communicated to end-users or used in further processing of t (...)

Have you ever wondered if deep learning is for you? You feel that you don't know math enough to understand what it is about or thought you need a supercomputer to train neural networks? Well, it's not entirely true. Some (...)

Automated video analysis is especially interesting from the perspective of modern branding, advertising, and bias-free communication. Microsoft Video Indexer can identify and tag some popular physical objects. We propose (...)