"The field of Machine Learning seeks to answer these questions: How can we build computer systems that automatically improve with experience, and what are the fundamental laws that govern all learning processes?"
– from The Discipline of Machine Learning by Tom Mitchell. CMU-ML-06-108, 2006.
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.
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."
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.
Microsoft today announced three new services that all aim to simplify the process of machine learning. These range from a new interface for a tool that completely automates the process of creating models, to a new no-code visual interface for building, training and deploying models, all the way to hosted Jupyter-style notebooks for advanced users. Getting started with machine learning is hard. Even to run the most basic of experiments takes a good amount of expertise. All of these new tools greatly simplify this process by hiding away the code or giving those who want to write their own code a pre-configured platform for doing so.
Over the past decade, designers have developed silicon technologies that run advanced deep learning mathematics fast enough to explore and implement artificial intelligence (AI) applications such as object identification, voice and facial recognition, and more. Machine vision applications, which are now often more accurate than a human, are one of the key functions driving new system-on-chip (SoC) investments to satisfy the development of AI for everyday applications. Using convolutional neural networks (CNNs) and other deep learning algorithms in vision applications have made such an impact that AI capabilities within SoCs are becoming pervasive. It was summarized effectively by Semico's 2018 AI Report "...some level of AI function in literally every type of silicon is strong and gaining momentum." In addition to vision, deep learning is used to solve complex problems such as 5G implementation for cellular infrastructure and simplifying 5G operational tasks through the capability to configure, optimize and repair itself, known as Self Organizing Networks (SON).
Google researchers developed a way to peer inside the minds of deep-learning systems, and the results are delightfully weird. What they did: The team built a tool that combines several techniques to provide people with a clearer idea of how neural networks make decisions. Applied to image classification, it lets a person visualize how the network develops its understanding of what is, for instance, a kitten or a Labrador. The visualizations, above, are ... strange. Why it matters: Deep learning is powerful--but opaque.
UBS Card Center, which processes roughly 25 percent of all credit cards in Switzerland, has won the Security Innovation of the Year award at the Retail Banker International Awards, presented in London. UBS Card Center's fraud team used the the latest artificial intelligence and machine learning capabilities in the FICO Falcon Platform to stop 84 percent more fraudulent transactions last year than in 2015. The need to optimise costs in the face of fierce competition meant UBS Card Center had to keep fraud write-offs to the very minimum. They were facing new fraud attack volumes but needed to uphold the highest standards for customer experience and satisfaction. This required the use of machine learning to minimize consumer interruptions while investigating more potential cases of fraud, all without adding staff.