Publications News

The November 2017 special issue of SPM on deep learning for visual understanding surveyed deep-learning solutions under reinforcement; weakly supervised and multimodal settings, investigated their robustness; and presented overviews of their applications in domain adaptation, hashing, semantic segmentation, metric learning, inverse problems in imaging, image-to-text generation, and picture-quality assessment.

Speech and Language processing (SLP) is essentially a series of sequence-to-sequence learning problems. Conventional SLP systems map input to output sequences through module-based architectures where each module is independently trained. 

Engineering safety and computer security have traditionally been viewed as separate fields: safety concentrates on the avoidance of physical harm; security protects information and privacy. When computers and physical plants did not interoperate, separation of safety and security was both reasonable and prudent. Given the advent of CPSs, we can no longer consider these problems as separate.

Cyber security is an increasing worry on many fronts, but typical discussions and headlines focus on very different types of threats than those experienced by aviation and space systems. Cyber security vulnerabilities compromise the control, traffic, navigation, and integrity of these systems. Countermeasures involve not only specialized systems and architectures, but often international cooperation, as the need for awareness extends well beyond the boundaries of a single aircraft.