A new automotive radar data set with measurements and point-wise annotations from more than four hours of driving is presented. Data provided by four series radar sensors mounted on one test vehicle were recorded and the individual detections of dynamic objects were manually grouped to clusters and labeled afterwards. The purpose of this data set is to enable the development of novel (machine learning-based) radar perception algorithms with the focus on moving road users. Images of the recorded sequences were captured using a documentary camera. For the evaluation of future object detection and classification algorithms, proposals for score calculation are made so that researchers can evaluate their algorithms on a common basis. Additional information as well as download instructions can be found on the website of the data set: www.radar-scenes.com.

Software trends come and go, but developers can future-proof their resumes with these major trends, industry experts say. Years ago, software developers could build a career on a single language, such as React.js, "Nowadays, there is so much blending between websites, e-commerce platforms, mobile applications, cloud and all the pieces in between that a developer has to learn multiple languages and frameworks," Schumann said. But while software development mainstays such as cloud computing and mobile apps are trends that endured, hundreds of others have faded into the annals of history, including LISP, marketing reporting software and storage tapes. This can make it a challenge for developers to decide which bandwagon to jump on.

Learn more about what comes next. Aware, a platform that analyzes employee behavior across messaging platforms like Slack, today announced that it raised $60 million in a series C round led by Goldman Sachs Growth Equity, with participation from Spring Mountain Capital, Blue Heron Capital, Allos Ventures, Ohio Innovation Fund, JobsOhio, and Rev1 Ventures. The company says that the capital, which brings its total raised to over $86.9 million, will be put toward product development, sales efforts, and hiring. "This specific investment will allow us to make significant progress towards helping organizations see the human difference across all functions of the business. We expect to rapidly expand our current integrations into new platforms, as well as to ingest and analyze digital signals from all areas of the organization," cofounder and CEO Jeff Schumann told VentureBeat via email.

The Linux Foundation on Tuesday announced the Open Voice Network, an open source association dedicated to advancing open standards that support the adoption of AI-enabled voice assistance systems. Organizations are beginning to develop, design, and manage their own voice assistant systems that are independent of today's general-purpose voice platforms. The desire to manage the entirety of the user experience is driving this transition. This control includes the sound of the voice, the sonic branding, and the content. The goal is to integrate voice assistance into multiple business processes and brand environments from the call center to the branch office and the store.

Today's operation of buildings is either based on simple dashboards that are not scalable to thousands of sensor data or on rules that provide very limited fault information only. In either case considerable manual effort is required for diagnosing building operation problems related to energy usage or occupant comfort. We present a Cognitive Building demo that uses (i) semantic reasoning to model physical relationships of sensors and systems, (ii) machine learning to predict and detect anomalies in energy flow, occupancy and user comfort, and (iii) speech-enabled Augmented Reality interfaces for immersive interaction with thousands of devices. Our demo analyzes data from more than 3,300 sensors and shows how we can automatically diagnose building operation problems.

Mobile phones can do lots of things: search the Web, download music, send e‑mail. But the vast majori ty of the 233 million Americans who own them never use them for more than calls and short text messages. One reason is that other features often require users to enter sentences or long search terms, a tedious task. Speech-recognition interfaces could make such features easier to use. Vlingo, a startup in Cambridge, MA, is coming to market with a simple user interface that provides speech recognition across mobile-phone applications.

We introduce a Maximum Entropy model able to capture the statistics of melodies in music. The model can be used to generate new melodies that emulate the style of the musical corpus which was used to train it. Instead of using the $n-$body interactions of $(n-1)-$order Markov models, traditionally used in automatic music generation, we use a $k-$nearest neighbour model with pairwise interactions only. In that way, we keep the number of parameters low and avoid over-fitting problems typical of Markov models. We show that long-range musical phrases don't need to be explicitly enforced using high-order Markov interactions, but can instead emerge from multiple, competing, pairwise interactions. We validate our Maximum Entropy model by contrasting how much the generated sequences capture the style of the original corpus without plagiarizing it. To this end we use a data-compression approach to discriminate the levels of borrowing and innovation featured by the artificial sequences. The results show that our modelling scheme outperforms both fixed-order and variable-order Markov models. This shows that, despite being based only on pairwise interactions, this Maximum Entropy scheme opens the possibility to generate musically sensible alterations of the original phrases, providing a way to generate innovation.

The goal of testing is to discriminate between multiple hypotheses about a system - for example, different fault diagnoses - by applying input patterns and verifying or falsifying the hypotheses from the observed outputs. Definitely discriminating tests (DDTs) are those input patterns that are guaranteed to discriminate between different hypotheses of non-deterministic systems. Finding DDTs is important in practice, but can be very expensive. Even more challenging is the problem of finding a DDT that minimizes the cost of the testing process, i.e., an input pattern that can be most cheaply enforced and that is a DDT. This paper addresses both problems. We show how we can transform a given problem into a Boolean structure in decomposable negation normal form (DNNF), and extract from it a Boolean formula whose models correspond to DDTs. This allows us to harness recent advances in both knowledge compilation and satisfiability for efficient and scalable DDT computation in practice. Furthermore, we show how we can generate a DNNF structure compactly encoding all DDTs of the problem and use it to obtain a cost-optimal DDT in time linear in the size of the structure. Experimental results from a real-world application show that our method can compute DDTs in less than 1 second for instances that were previously intractable, and cost-optimal DDTs in less than 20 seconds where previous approaches could not even compute an arbitrary DDT.