We propose the SupRB learning system, a new Pittsburgh-style learning classifier system (LCS) for supervised learning on multi-dimensional continuous decision problems. SupRB learns an approximation of a quality function from examples (consisting of situations, choices and associated qualities) and is then able to make an optimal choice as well as predict the quality of a choice in a given situation. One area of application for SupRB is parametrization of industrial machinery. In this field, acceptance of the recommendations of machine learning systems is highly reliant on operators' trust. While an essential and much-researched ingredient for that trust is prediction quality, it seems that this alone is not enough. At least as important is a human-understandable explanation of the reasoning behind a recommendation. While many state-of-the-art methods such as artificial neural networks fall short of this, LCSs such as SupRB provide human-readable rules that can be understood very easily. The prevalent LCSs are not directly applicable to this problem as they lack support for continuous choices. This paper lays the foundations for SupRB and shows its general applicability on a simplified model of an additive manufacturing problem.

Every few seconds there is a small puff of smoke as a weed keels over, having been zapped with a high voltage. The device doing the zapping is a prototype weeding robot developed by the Small Robot Company, a new firm operating out of an old munitions depot near Salisbury, in south-west Britain. Such machines, called "agribots", are appearing in many shapes and sizes from a variety of companies. Muddy tracks from other prototypes lead into the Small Robot Company's workshop, where a row of 3D printers make bright orange components out of plastic. That makes parts easier to find should they fall off in a field, which is a sure sign that farmers are at work here, with roboticists and scientists.

A mummified Ancient Egyptian priest is talking from beyond the grave thanks to modern technology. Nesyamun, a priest at the time of pharaoh Ramses II the Pharaohs was mummified around 3,000 years ago. His remains are so well preserved that scientists were able to map his throat, mouth and voice box using a CT scanner at Leeds General Infirmary, and recreate it using 3D printing. The priest, who is normally on display at Leeds museum, was first unwrapped in 1824 and has'true of voice' inscribed on his coffin. Academics believe his voice would have produced a vowel-like sound -- somewhere between an'a' and'e' noise.

Robotics have a mixed history in construction. Some work, especially in prefabricated building offsite, while others have not been successful, particularly when used onsite. However, that may be changing as more equipment companies are exploring the use of robotic technology and applying it to construction. One of the technologies that has shown promise is in the use of robotic arms and gantry equipment for 3D printing of concrete walls. From one of the first, if not the first, completed buildings constructed in this method, an office building in Dubai, to the research work being done by Chinese and U.S. companies as well as others in the European Union, building onsite using what is referred to as additive manufacturing techniques is moving rapidly.

Diffractive deep neural network is an optical machine learning framework that blends deep learning with optical diffraction and light-matter interaction to engineer diffractive surfaces that collectively perform optical computation at the speed of light. A diffractive neural network is first designed in a computer using deep learning techniques, followed by the physical fabrication of the designed layers of the neural network using e.g., 3-D printing or lithography. Since the connection between the input and output planes of a diffractive neural network is established via diffraction of light through passive layers, the inference process and the associated optical computation does not consume any power except the light used to illuminate the object of interest. Developed by researchers at UCLA, diffractive optical networks provide a low power, low latency and highly-scalable machine learning platform that can find numerous applications in robotics, autonomous vehicles, defense industry, among many others. In addition to providing statistical inference and generalization to classes of data, diffractive neural networks have also been used to design deterministic optical systems such as a thin imaging system.

Most 3D-printed objects are prototypes or one-off creations, in large part because 3D printing is more finicky than traditional manufacturing. Because the process works by adding layers of material atop each other, subtle changes in temperatures or material quality can result in imperfections and hours of lost work. Inkbit, a Boston-area 3D printing company, is using machine vision and artificial intelligence to help its equipment course correct. Javier Ramos, co-founder and director of hardware at Inkbit, said Inkbit's machine vision technology instantly scans the objects it prints, relying on AI to correct for any mistakes made. He imagines a future where Inkbit's tech is used on every factory floor, printing out millions of products more cheaply -- and faster -- than traditional manufacturing processes ever could.

A savvy approach to artificial intelligence can radically enhance productivity and slash costs. You're not imagining it: the pace of technological change is indeed quickening and it's placing tremendous competitive pressures on every corner of the global economy Manufacturers are acutely feeling the squeeze. Eighty-five percent of industrial equipment execs surveyed by Accenture say they need to innovate ever faster just to keep up. That puts them in a perilous catch-22: it's prohibitively expensive to upgrade equipment to meet customer demands, yet they risk losing customers altogether if they don't. Enter artificial intelligence, the great equalizer for manufacturers.

Objects made with 3D printing can be lighter, stronger, and more complex than those produced through traditional manufacturing methods. But several technical challenges must be overcome before 3D printing transforms the production of most devices. Commercially available printers generally offer only high-speed, high-precision, or high-quality materials. Rarely do they offer all three, limiting their usefulness as a manufacturing tool. Today, 3D printing is used mainly for prototyping and low-volume production of specialized parts.

The company is accomplishing this by pairing its multimaterial inkjet 3D printer with machine-vision and machine–learning systems.

However, most commercial printers are only able to build objects from a single material at a time and inkjet printers that are capable of multimaterial printing are constrained by the physics of droplet formation. Extrusion-based 3D printing allows a broad palette of materials to be printed, but the process is extremely slow. For example, it would take roughly 10 days to build a 3D object roughly one liter in volume at the resolution of a human hair and print speed of 10 cm/s using a single-nozzle, single-material printhead. To build the same object in less than 1 day, one would need to implement a printhead with 16 nozzles printing simultaneously! Now, a new technique called multimaterial multinozzle 3D (MM3D) printing developed at Harvard's Wyss Institute for Biologically Inspired Engineering and John A. Paulson School of Engineering and Applied Sciences (SEAS) uses high-speed pressure valves to achieve rapid, continuous, and seamless switching between up to eight different printing materials, enabling the creation of complex shapes in a fraction of the time currently required using printheads that range from a single nozzle to large multinozzle arrays.