Black box machine learning models are currently being used for high-stakes decision making throughout society, causing problems in healthcare, criminal justice and other domains. Some people hope that creating methods for explaining these black box models will alleviate some of the problems, but trying to explain black box models, rather than creating models that are interpretable in the first place, is likely to perpetuate bad practice and can potentially cause great harm to society. The way forward is to design models that are inherently interpretable. This Perspective clarifies the chasm between explaining black boxes and using inherently interpretable models, outlines several key reasons why explainable black boxes should be avoided in high-stakes decisions, identifies challenges to interpretable machine learning, and provides several example applications where interpretable models could potentially replace black box models in criminal justice, healthcare and computer vision.
A new area in artificial intelligence involves using algorithms to automatically design machine-learning systems known as neural networks, which are more accurate and efficient than those developed by human engineers. But this so-called neural architecture search (NAS) technique is computationally expensive. A state-of-the-art NAS algorithm recently developed by Google to run on a squad of graphical processing units (GPUs) took 48,000 GPU hours to produce a single convolutional neural network, which is used for image classification and detection tasks. Google has the wherewithal to run hundreds of GPUs and other specialized hardware in parallel, but that's out of reach for many others. In a paper being presented at the International Conference on Learning Representations in May, MIT researchers describe an NAS algorithm that can directly learn specialized convolutional neural networks (CNNs) for target hardware platforms -- when run on a massive image dataset -- in only 200 GPU hours, which could enable far broader use of these types of algorithms.
The current availability of ever-increasing computational power, highly developed pattern recognition algorithms and advanced image processing software working at very high speeds has led to the emergence of computer-based systems that are trained to perform complex tasks in bioinformatics, medical imaging and medical robotics. Accessibility to'big data' enables the'cognitive' computer to scan billions of bits of unstructured information, extract the relevant information and recognize complex patterns with increasing confidence. Computer-based decision-support systems based on machine learning (ML) have the potential to revolutionize medicine by performing complex tasks that are currently assigned to specialists to improve diagnostic accuracy, increase efficiency of throughputs, improve clinical workflow, decrease human resource costs and improve treatment choices. These characteristics could be especially helpful in the management of prostate cancer, with growing applications in diagnostic imaging, surgical interventions, skills training and assessment, digital pathology and genomics. Medicine must adapt to this changing world, and urologists, oncologists, radiologists and pathologists, as high-volume users of imaging and pathology, need to understand this burgeoning science and acknowledge that the development of highly accurate AI-based decision-support applications of ML will require collaboration between data scientists, computer researchers and engineers.
Microsoft and Mojang have announced a new Minecraft game, 'Minecraft Earth,' for mobile devices, which uses augmented reality to place objects from the game in your real world. Minecraft is expanding its reach – into your real world. A new game, "Minecraft Earth," coming this summer for mobile devices (Android and iOS), uses augmented reality – à la "Pokémon Go" – to let you find objects in real-world locations and place objects from the game there, too. "The game's mechanics are simple: explore your neighborhood to find blocks and unique mobs for your builds. Once you have them, any flat surface is an opportunity to build," said Minecraft creative director Saxs Persson in a post on Xbox.com.
Want to feel really depressed about the likely impact of climate change? AI can help with that. A new research paper shows how machine-learning trickery can highlight the ravages of climate change--by revealing how a property is likely to be harmed by rising sea levels, fiercer storms, and other disasters that it's expected to worsen. Changes afoot: The researchers used an increasingly popular technique to automatically conjure up submerged and damaged properties. As they write in their paper: "The eventual goal of our project is to enable individuals to make more informed choices about their climate future by creating a more visceral understanding of the effects of climate change."
A self-driving shuttle got pulled over by police on its first day carrying passengers on a new Rhode Island route. Providence Police Chief Hugh Clements says an officer pulled over the odd-looking autonomous vehicle because he had never seen one before. The bus-like vehicle operated by Michigan-based May Mobility was dropping off passengers Wednesday morning when a police cruiser arrived with blinking lights and a siren. It was just hours after the public launch of a state-funded pilot shuttle service. The shuttle offers free rides on a 12-stop urban loop.
The Dali Museum in St Petersburg, Florida, got an AI to study archive footage of the great artist and recreate him as a deepfake. Microsoft will help you mind your Ps and LGBTQs with a version of Office that checks documents for inclusive language, such as changing "housewives" to "homemakers". People are coming for robot jobs. Japanese start-up Mira Robotics will soon sell a robot butler – the catch is it is controlled remotely by a human. The Orbital Reflector, a piece of "space art" in the form of a shimmering balloon, has failed in orbit.
The deep learning algorithms of artificial intelligence can identify patterns that help inventors think laterally, make connections between nonobvious ideas, pinpoint hidden invention features, and exploit new science and technology-based opportunities. "To invent, you need a good imagination and a pile of junk." So said Thomas Edison, America's most prolific inventor. Yet the march of technology is now changing the great man's inventive equation: powerful algorithmic advisory systems are now giving inventors far more fertile imaginations, even if they don't have very much of one themselves. After being fed vast datasets of information on a field of inventive endeavor, deep learning algorithms identify patterns that help inventors think laterally, make connections between nonobvious ideas, pinpoint hidden invention features that rivals have missed, and exploit new science and technology-based opportunities from, say, patents and journals.