Principal Investigator Admir Masic
Principal Investigator J Perron
Hear from panelists from both large corporations and startups to discuss the challenges and successes of engaging with the other and working together. Now more than ever, collaborative innovation is essential for growth and combating (or leading) market disruption. Startups allow large companies to develop and test new technologies with less risk and overhead; meanwhile, corporations offer advantages of a large network, greater resources, brand recognition, and market knowledge and experience for startups. Collaborating should be a win-win scenario; however, best practices and approach may not always be obvious (or easy) when crossing lines.
Companies are racing to implement AI to better their businesses; however, most have yet to see results. While your company might have the magic algorithm, there’s a good chance it does not have quality data to yet gain insights. The data most organizations currently have was not gathered or created with machine learning in mind; rather, it was traditionally used for measuring physical and financial assets. But how could these same measures apply in a marketplace where the majority of assets are now intangible? In order for your data (and insights) to have meaning, it must be curated around key knowledge and differentiated from your competitors’ data. When making important decisions, what matters most to your company? How can you capture this knowledge and data to make the best use of it?
Moderator: Margaret Childs Panels: Sinan Aral, Frank Schweitzer, Shermin Voshmgir We’re in a continuous struggle to combat falsity. It’s a Wild, Wild West with verification a moving target. New digital media platforms based on block chain can run applications exactly as programmed without the possibility of downtime, censorship, fraud, or third-party interference. Still, we do not know enough about the phenomenon of falsity and why it spreads so readily on digital media. But, we may be closer to answers—and interventions—since we now have data at scale and are on the brink of a revolution understanding how humans behave. The panel will discuss possible interventions to mitigate and hopefully prevent the spread of falsity including how new digital media platforms will algorithmically redefine confirmation, validation, and value. How could blockchain and tokenization of social media based on examples like provide a solution to these problem? What can we learn from early blockchain use cases like Steemit, Basic Attention Token (BAT), and Token Curated Registries (TCRs).
Video can be used as the input data for the real-time monitoring of machines, products, or processes to which sensors cannot be affixed. Industrial and scientific monitoring applications, compared to other video sources, such as those from surveillance, broadcast, mobile robotics, social media, or entertainment, can often be engineered and structured. Yet, applications of video-based instrumentation in industrial, manufacturing, and scientific experimentation environments are not extensively addressed by the computer vision community.
We discuss the needs, challenges, and recent success in deploying real-time, data-science enabled techniques to efficiently reduce the complexity and dimensionality of raw video data to extract actionable information for real-time feedback and process control, defect detection, and wear and degradation related for factories and the factory subsystem.