Voice assistants can detect typing on nearby devices, which could potentially be used to work out what a person is writing on their phone from up to half a metre away. Ilia Shumailov at the University of Cambridge and his colleagues built a machine-learning system that could recognise the sound of tapping on a touchscreen and combined it with other artificial intelligence tools to try to determine what people were typing.
New drones equipped with a deep learning application that improves the images they collect during search and rescue missions can better distinguish people from their surroundings. Researchers from Austria's Johannes Kepler University have developed drones equipped with a deep learning application that improves the images they collect during search and rescue missions to better distinguish people from their surroundings. The team noted, "automated person detection under occlusion conditions can be notably improved by combining multi-perspective images before classification." The researchers achieved 96% precision and 93% recall rates with image integration using airborne optical sectioning, a synthetic aperture imaging technique that captures unstructured thermal light fields using camera drones, compared to 25% achieved by traditional thermal imaging. The researchers say the drones are ready for use.
In September 2019, the National Institute of Standards and Technology issued its first-ever warning for an attack on a commercial artificial intelligence algorithm. Security researchers had devised a way to attack a Proofpoint product that uses machine learning to identify spam emails. The system produced email headers that included a "score" of how likely a message was to be spam. But analyzing these scores, along with the contents of messages, made it possible to build a clone of the machine-learning model and craft spam messages that evaded detection. The vulnerability notice may be the first of many.
Project Loon is using balloons such as this to set up an aerial wireless network for telecommunications.Credit: Loon The goal of an autonomous machine is to achieve an objective by making decisions while negotiating a dynamic environment. Given complete knowledge of a system's current state, artificial intelligence and machine learning can excel at this, and even outperform humans at certain tasks -- for example, when playing arcade and turn-based board games1. But beyond the idealized world of games, real-world deployment of automated machines is hampered by environments that can be noisy and chaotic, and which are not adequately observed. The difficulty of devising long-term strategies from incomplete data can also hinder the operation of independent AI agents in real-world challenges. Writing in Nature, Bellemare et al.2 describe a way forward by demonstrating that stratospheric balloons, guided by AI, can pursue a long-term strategy for positioning themselves about a location on the Equator, even when precise knowledge of buffeting winds is not known.