If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
Cher Horowitz's closet from the film "Clueless" had a futuristic computer system that helped her put together outfits. Back in 1995, the concept teased what it might be like to get dressed in the future. Technology has evolved a lot since then, but closets have been largely untouched by innovation. Now, that's starting to change. "If algorithms do their job well, people will spend less time thinking about what to wear," said Ranjitha Kumar, an assistant professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign.
How do you find errors in a system that exists in a black box whose contents are a mystery even to experts? That is one of the challenges of perfecting self-driving cars and other deep learning systems that are based on artificial neural networks--known as deep neural networks--modeled after the human brain. Inside these systems, a web of neurons enables a machine to process data with a nonlinear approach and, essentially, to teach itself to analyze information through what is known as training data. When an input is presented to a "trained" system--like an image of a typical two-lane highway shown to a self-driving car platform--the system recognizes it by running an analysis through its complex logic system. This process largely occurs inside a black box and is not fully understood by anyone, including a system's creators.
Practical machine learning development has advanced at a remarkable pace. This is reflected by not only a rise in actual products based on, or offering, machine learning capabilities but also a rise in new development frameworks and methodologies, most of which are backed by open-source projects. In fact, developers and researchers beginning a new project can be easily overwhelmed by the choice of frameworks offered out there. These new tools vary considerably -- and striking a balance between keeping up with new trends and ensuring project stability and reliability can be hard. The list below describes five of the most popular open-source machine learning frameworks, what they offer, and what use cases they can best be applied to.
Work as we know it is in a state of flux. Technology is imposing rapid change, and the rise in automation capabilities and artificial intelligence are the chief catalysts. As Salesforce's Futurist, I spend a lot of time forward-thinking and analysing trend data, and have shared my thoughts on what this technological change means for the future of work and how to navigate it. There's a lot of angst in the world right now that the rise of smart technologies are going to disemploy vast numbers of people. I appreciate why there's anxiety, but if we look at history as a predictor of the future, this simplistic idea that'technology steals jobs' is unfounded.
Microsoft announced today that its Visual Studio integrated development environment is getting a new set of tools aimed at easing the process of building AI systems. Visual Studio Tools for AI is a package that's designed to provide developers with built-in support for creating applications with a wide variety of machine learning frameworks, like Caffe2, TensorFlow, CNTK, and MXNet. Once users have coded up models inside Visual Studio, the AI tools make it easier for them to send that code off to Microsoft's Azure cloud platform for training and deployment. Launching these tools brings a host of advanced capabilities to developers in a point-and-click format that would have previously required the use of a command line interface. It should make building AI systems more accessible for a class of developers that haven't been able to use Visual Studio's rich development environment to its full potential for that purpose.
Remember the saying, "there's an app for that"? It may be the case that there are too many apps for "that" these days. The number of available apps in the Google Play Store was placed at 3.3 million apps in September 2017. Apple's App Store is the second-largest app store with 2.2 million available apps. In such a cluttered space, even the best apps struggle to find an audience.
Users of R have long been deprived of the opportunity to join the deep learning movement while remaining within the same programming language. With the release of MXNet, the situation began to change, but the frequent updates to the original documentation and changes that break backward compatibility still limit the popularity of this library. TensorFlow, Theano, CNTK) combined with detailed documentation and a lot of examples looks much more attractive. This article presents a solution to the problem of segmenting images in Carvana Image Masking Challenge, in which you want to learn how to separate cars photographed from 16 different angles will be dismantled. The neural network part is fully implemented on Keras, image processing is answered by magick (interface to ImageMagick), and parallel processing is provided by parallel doParallel foreach (Windows) or parallel doMC foreach (Linux).
Amazon yesterday announced its ONNX-MXNet package to import Open Neural Network Exchange (ONNX) deep learning models into Apache MXNet, signifying the company is on-board with Facebook and Microsoft in efforts to open-source AI. With the ONNX-MXNet Python package, developers running models based on open-source ONNX will be able to run them on Apache MXNet. Basically, this allows AI developers to keep models but switch networks, as opposed to starting from scratch. If you can imagine a thousand start ups and another thousand universities all creating at the bleeding edge of machine learning technology, but unable to share work due to'format' issues, you won't be very far off from the state of things without initiatives like ONNX. With Facebook and Microsoft all-in on the idea of open-source AI platforms, and now Amazon joining them, it's looking like ONNX is the path forward.
IBM announced new software to deliver faster time to insight for high performance data analytics (HPDA) workloads, such as Spark, Tensor Flow and Caffé, for AI, Machine Learning and Deep Learning. Based on the same software, which will be deployed for the Department of Energy's CORAL Supercomputer Project at both Oak Ridge and Lawrence Livermore, IBM will enable new solutions for any enterprise running HPDA workloads. New to this launch is Deep Learning Impact (DLI), a set of software tools to help users develop AI models with the leading open source deep learning frameworks, like TensorFlow and Caffe. The DLI tools are complementary to the PowerAI deep learning enterprise software distribution already available from IBM. Also new is web access and simplified user interfaces for IBM Spectrum LSF Suites, combining a powerful workload management platform with the flexibility of remote access.
To help increase developers' productivity and simplify app development, Microsoft has announced new data platform technologies and cross-platform developer tools. The company launched a new AI-powered platform "Azure Databricks" during an event for developers late Thursday. Designed in collaboration with the founders of Apache Spark, Azure Databricks analytics platform delivers one-click setup, streamlined workflows and an interactive workspace. The platform will enable organisations to provide self-service analytics and machine learning over all data with enterprise-grade performance and governance, Microsoft said in a statement. "With today's intelligent cloud, emerging technologies like Artificial Intelligence (AI) have the potential to change every facet of how we interact with the world," said Scott Guthrie, Executive Vice President.