Generative adversarial networks -- GANs for short -- are making waves in the world of machine learning. Yann LeCun, a legend in the deep learning community, said in a Quora post "[GANs are] the most interesting idea in the last 10 years in [machine learning]." GANs (and, more generally, neural networks) can be confusing at first. But developers have created lots of great frameworks for training pre-configured models efficiently. We'll examine a package built by Hyeonwoo Kang at Catholic University of Korea that wraps PyTorch implementations for ten different types of GANs in an easy-to-use interface.

We all know that artificial intelligence is rapidly expanding in different industries, but what if we told you that AI can now be used in healthcare as well? A new AI technology has been developed to be used in the medical setting, specifically in detecting genetic disorders in humans. The AI, called Deep Gestalt, can identify genetic disorders just by looking at a patient's face, using different markers to accurately guess the specific disorder. In a recent study published by the journal Nature Magazine, Deep Gestalt even managed to outperform human physicians in three separate clinical trials. During the experiment, it was given a couple of photographs that showed a person with a genetic disorder. Most genetic disorders have specific markers that differentiate them from one another, and Deep Gestalt used deep learning to teach itself these markers.

The image above has been cropped. Could cervical cancer be brought under control? Not quite, but the results of a study published in the Journal of the National Cancer Institute seem promising. Researchers from the National Institutes of Health and Global Good have developed a deep learning algorithm that can analyze digital images of a woman's cervix and identify precancerous changes that require medical attention -- with more accuracy than human experts. The team used comprehensive datasets to train the algorithm to recognize patterns in complex visual inputs, like medical images.

Developing neural networks is often referred to as a dark art. The reason for this is that being skilled at developing neural network models comes from experience. There are no reliable methods to analytically calculate how to design a "good" or "best" model for your specific dataset. You must draw on experience and experiment in order to discover what works on your problem. A lot of this experience can come from actually developing neural networks on test problems.

In this notebook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator?

YOLOv3 is one of the most popular real-time object detectors in Computer Vision. In our previous post, we shared how to use YOLOv3 in an OpenCV application. It was very well received and many readers asked us to write a post on how to train YOLOv3 for new objects (i.e. In this step-by-step tutorial, we start with a simple case of how to train a 1-class object detector using YOLOv3. The tutorial is written with beginners in mind. Continuing with the spirit of the holidays, we will build our own snowman detector.

Facebook offers a one-year research training position composed to give aspirants hands-on experience with machine learning research while working in Facebook AI groups. The programme aims aspirants to join with an AI Researcher and Engineer who will both guide their project. As a team, candidates will pick a research problem of mutual interest and then design new deep learning techniques to solve the problem. The research candidates are to communicate with the academic community by submitting papers to top academic venues (for example NeurIPS, ICML, ICLR, CVPR, ICCV, ACL, EMNLP etc.), as well as open-source code releases. The AI Residency event is designed to prepare aspirants for graduate programs in machine learning or to kickstart a career in the field.

Financial markets are complex to understand. Stock markets generate a huge amount of data and this data. Big banks and hedge funds are making use of artificial intelligence and machine learning algorithms to automate the process of trading. Machine learning applications have improved the everyday banking, payment systems and more powerful insight into the financial sector. Machine Learning service is making the banking and financial sector smarter.

Deep Learning is very computationally intensive, so you will need a fast CPU with many cores, right? Or is it maybe wasteful to buy a fast CPU? One of the worst things you can do when building a deep learning system is to waste money on hardware that is unnecessary. Here I will guide you step by step through the hardware you will need for a cheap high-performance system. Over the years, I build a total of 7 different deep learning workstations and despite careful research and reasoning, I made my fair share of mistake in selecting hardware parts. In this guide, I want to share my experience that I gained over the years so that you do not make the same mistakes that I did before. The blog post is ordered by mistake severity. This means the mistakes where people usually waste the most money come first.

Advances in artificial intelligence (AI) are happening at a much quicker pace than anyone could have predicted. This emerging technology is now being used by businesses and is even finding its way into consumer products. One industry that has fully embraced AI is healthcare and doctors and other hospital staff are using advanced machine learning algorithms to solve problems in new ways. TechRadar Pro spoke with HeartFlow's Founder and Chief Technology Officer Charles A. Taylor to learn more about how the company is using deep learning to build 3-D models of patients' hearts to provide doctors with a safer and more effective way of diagnosing cardiovascular disease. HeartFlow has pioneered technology to help clinicians diagnose coronary heart disease (CHD).