Principal Investigator Ethan Zuckerman
Principal Investigator Charles Fine
Principal Investigator Tyler Jacks
Principal Investigator Dara Entekhabi
Visual object detection and recognition are needed for a wide range of applications including robotics/drones, self-driving cars, smart Internet of Things, and portable/wearable electronics. For many of these applications, local embedded processing is preferred due to privacy or latency concerns. In this talk, we will describe how joint algorithm and hardware design can be used to reduce the energy consumption of object detection and recognition while delivering real-time and robust performance. We will discuss several energy-efficient techniques that exploit sparsity, reduce data movement and storage costs, and show how they can be applied to popular forms of object detection and recognition, including those that use deep convolutional neural nets (CNNs). We will present results from recently fabricated ASICs (including our deep CNN accelerator named “Eyeriss” which is 10x more energy efficient than a mobile GPU) that demonstrate these techniques in real-time computer vision systems.
How can you protect yourself against threats you don’t know about? What measures can you take to assess your risk before a breach? How can you protect yourself against an attack that originates in an innocuous object like a toaster? Professor John Williams will discuss how organizations can prepare themselves to defend against cybersecurity threats to protect their enterprises. He will discussrisk a modeling and data analytics tool (Saffron), that helps to identify risk tolerance and strategies for assessing, responding to, and monitoring cyber security risks.
Twenty years ago the idea of speaking with a chatbot to resolve a problem was unheard of. Today we can ask Siri to make us a reservation for a nearby restaurant with the touch of a button. Artificial intelligence, wearables, virtual reality, and the Internet of Things are rapidly changing the world around us. From clothing that can track your fatigue to the changes in the process of booking a hotel room, Professor Casalegno will discuss the future of these technologies and where they will take us.
OPAL/Enigma is a new paradigm for data sharing across organizations in a privacy-preserving manner. OPAL (Open Algorithms) allows for scalable querying of data-sets that are physically spread across the Internet, and owned by different organizations. Rather than moving data to a centralized querier location, it is the query (algorithm) that is sent to the data repository. Raw data never leaves its repository, and it is in an encrypted at all times -- during storage and computation. The Enigma phases consist of using the nodes of the P2P network, such as in a blockchain, to split encrypted data and storing these pieces on the nodes of the P2P network. Computation is then based on these pieces of encrypted data stored on the nodes.