From autonomous vehicles to autonomous markets, it is becoming clear that solutions comprised of autonomous intelligent agents are changing the way we get things done. In situations involving “person-in-the-loop” style
From autonomous vehicles to autonomous markets, it is becoming clear that solutions comprised of autonomous intelligent agents are changing the way we get things done. In situations involving “person-in-the-loop” style systems, we continue to push the human operator out of the tighter, faster inner loops and into a more supervisory role. This push from the center is for good reason: for what autonomous systems lack in ingenuity, they make up for in untiring and unrelenting attention and speed.
More importantly, recent advances in the field of machine learning empower computer systems to “discover” hidden insights within data, exposing hidden correlations and conclusions normally obscured by the complexity and enormity of the available data. This allows for the creation of tools that act as a force multiplier, allowing the benefit of the properties of large data sets while providing the human decision maker on the other end with a higher level of understanding of the meaning of its contents.
It is our view that the automation of the attention intensive tasks of detection, identification, classification and location of bespoke signals and systems will lead to the faster, better insights required for providing actionable decision support. The AI techniques implemented allow for a significant force multiplier by utilizing the richness of large data sets that are being generated at a rate of greater than 100GB/min, while providing the operator with a better understanding of the meaning of its contents.
To enable guided spectrum operations at the tactical edge, computationally intensive tasks must perform real-time DSP and machine learning in platforms with low SWaP-C requirements. Such platforms will need to overcome integration, interoperability and scalability challenges with the latest in data processing and data sharing techniques.
This seminar will discuss an AI system that is computationally efficient, scalable and in compliance with the Defense Innovation Board Recommendations on AI Ethical Guidelines.
mostra di più
Tutto il giorno (Giovedì)