Artificial Intelligence

Our goal is to enable applications of artificial intelligence (AI) in complex problems vision, science, control, and optimization., as well as instigate orders of magnitude gains in energy-efficiency of AI platforms for internet-of-things (IoT) system.  The key research vectors are:

  1. Learning Algorithms and Applications: GREEN Lab is interested in developing innovative learning algorithms and application of existing learning algorithms such as deep neural network, spiking neural network, and  dynamical systems to problems in computer vision, science, control, and optimization.
    • Embedded Computer Vision: We are developing AI/ML algorithms that can be embedded in cameras to enhance information content of sensed images/videos.
    • Dynamical Systems: We are developing models that can learn dynamics of a complex system to enable prediction of the system’s evolution.
    • Artificial Intelligence for Science:  We are developing a hybrid learning theory for applying AI to scientific problems that couples model-based learning of system’s dynamics with data driven learning.
    •  AI/ML in Control and Optimization: We are interested in applications of AI and ML in treal-time control systems and optimization problems.
    • AI/ML in Radio Frequency and Radar Processing: We are interested in AI/ML algorithms and hardware accelerators for high-bandwidth Radio Frequency and Radar applications.
  2. Reliable Intelligence in Unreliable Environment: We are exploring algorithmic techniques to enhance reliability and resiliency of AI/ML methods even in unreliable environment. The unreliability can be due noise and uncertainty in external environment, sensor, AI/ML model, or processing hardware.
    • Uncertainty Quantification and Estimation: We are developing methods for uncertainty quantification as well as methods for fast real-time uncertainty estimations.
    • Noise-robust Deep Learning:  We are characterizing and reducing the effect of noise in the accuracy of deep learning algorithms.
    • Secure Deep Learning: We are developing training algorithms and defense mechanisms to make deep neural networks secure against adversarial attacks.
  3. Closed-loop Perception for Autonomous Systems. The pereception modules in today’s autonomous system are inherently open-loop i.e. sensors acquire data, perception modules process and fuse sensor data, and control module use the output to generate control action.  We are developing a new paradigm of closed-loop approach to perception for autonomous vehicles to (i) reduce perception latency, (ii) improve compute and sensor resource utilization, (iii) reduce perception failures, and (iv) ensure quality of decision making and planning. This will require a cohesive approach connecting intelligent sensors, efficient perception algorithms, as well as real-time control principles.
  4. Collaborative Learning: We believe enabling intelligence in future internet-of-things (IoT) system will require active collaboration between multiple edge devices and between edge and cloud. We are exploring collaboration between edge and host, where a host running complex deep learning guides a simple (non-AI) edge device to increase quality of information delivered from edge to host under constrained bandwidth. We are exploring how learning algorithms can be partitioned between host and edge, or between multiple edge devices to enable collaborative learning and enhance energy-efficient and quality-of-service in an IoT environment.