A noteworthy achievement of artificial intelligence, since it is driven by artificial neural networks under the label deep learning, is the ability to create artistic works to generate images, text and sounds. At the core of this breakthrough is a basic method to train neural networks that was introduced by Ian Goodfellow in 2014 and was called by Yann LeCun “the most interesting idea in the last 10 years in machine learning”: generative adversarial networks (GANs). A GAN is a way to train a generative network that produces realistic-looking fake samples out of a latent seed, which can be some arbitrary data or random numbers sampled from a simple distribution. Let’s look at how to do so with some of the new capabilities developed for Mathematica Version 12.1.
As more technology is folded into medical environments all over the world, Wolfram’s European branch has taken on work with the United Kingdom’s National Health Service (NHS) in an effort to partially automate the process of cancer diagnosis. The task is to use machine learning to avoid checking thousands of similar-looking images of people’s insides by hand for signs of cancer.
Version 12.1 of the Wolfram Language introduces the long-awaited Video object. The Video object is completely (and only) out-of-core; it can link to an extensive list of video containers with almost any codec. Most importantly, it is bundled with complete stacks for image and audio processing, machine learning and neural nets, statistics and visualization and many more capabilities. This already makes the Wolfram Language a powerful video computation platform, but there are still more features to explore.
Today, the world around us is being captured by imaging devices ranging from cell phones and action cameras to microscopes and telescopes. With ever-increasing generation of images, image processing and automatic image analysis are used in a wide range of individual, academic and industry applications.
We are excited to announce Introduction to Image Processing, a free interactive course from Wolfram U, which makes cutting-edge image processing simple with graphical and visual examples that demonstrate how image operations work. It includes 14 video lessons, each lasting 20 minutes or fewer, and 5 short quizzes, as well as a certificate for finishing all course materials. Topics range from how to control brightness and contrast or crop and resize images, to advanced topics including segmentation, image enhancement, feature detection and using machine learning to perform modern image processing—no machine learning knowledge necessary!
For many of us, programming represents leisure time just as much as work. Here at Wolfram, we have an incredibly creative group with a wide variety of hobbies, on the screen and off—including textile arts like cross-stitch. So when my colleague Jay suggested that I create a cross-stitch program using the Wolfram Language, I replied with “Challenge accepted!” Jay was looking for a simple way to generate a cross-stitch pattern from a photograph—or really any image—with the colors corresponding to the DMC thread ID numbers. We both knew that the image-processing capabilities of the Wolfram Language would make this an easy task, but incorporating the DMC thread catalog seemed a more interesting challenge. Armed with both computer and (virtual) thread, I set out on my quest to create the perfect cross-stitch pattern generator.
If you haven’t used machine learning, deep learning and neural networks yourself, you’ve almost certainly heard of them. You may be familiar with their commercial use in self-driving cars, image recognition, automatic text completion, text translation and other complex data analysis, but you can also train your own neural nets to accomplish tasks like identifying objects in images, generating sequences of text or segmenting pixels of an image. With the Wolfram Language, you can get started with machine learning and neural nets faster than you think. Since deep learning and neural networks are everywhere, let’s go ahead and explore what exactly they are and how you can start using them.