Magnetic Resonance Imaging (MRI) can be accelerated by sampling below the Shannon-Nyquist rate via compressed sensing techniques. In this talk, I will consider the problem of optimizing the under-sampling pattern in a data-driven fashion, which has been an open problem for over a decade. For a given sparsity constraint, our method optimizes the under-sampling pattern […]
Classical and quantum photonics with superior properties can be implemented in a variety of old (silicon, silicon nitride) and new (silicon carbide, diamond) photonic materials by combining state of the art optimization and machine learning techniques (photonics inverse design) with new fabrication approaches. In addition to making photonics more robust to errors in fabrication and […]
Open-source software has been a critical enabler for tremendous innovation in the software ecosystem over the past two decades. Inspired by this success, open-source hardware involves making the high-level description of hardware components freely available for others to study, change, distribute, and ultimately use in fabricating their own hardware components. Unfortunately, open-source hardware has had […]
Miniaturized light sources are critical for next-generation on-chip photonic devices. Plasmon-based lasers and surface plasmon amplified spontaneous emission of radiation (spasers) have received significant attention since their prediction over a decay over a decade ago. Major advances have included subwavelength footprint sizes, room-temperature operation, far-field emission directionality, and understanding of the lasing mechanism. Notably, one […]
Overparameterized neural networks have proved to be remarkably successful in many complex tasks such as image classification and deep reinforcement learning. In this talk, we will consider the role of explicit regularization in training overparameterized neural networks. Specifically, we consider ReLU networks and show that the landscape of commonly used regularized loss functions have the […]
The strong lottery ticket hypothesis (LTH) postulates that any neural network can be approximated by simply pruning a sufficiently larger network of random weights. Recent work establishes that the strong LTH is true if the random network to be pruned is a large poly-factor wider than the target one. This polynomial over-parameterization is at odds with […]
Abstract: The fundamental issue underlying natural language understanding is that of semantics – there is a need to move toward understanding natural language at an appropriate level of abstraction in order to support natural language understanding and communication with computers.
Machine Learning has become ubiquitous in our attempt to induce semantic representations of natural language and support decisions that depend on it; however, while we have made significant progress over the last few years, it has focused on classification tasks for which we have large amounts of annotated data. Supporting high level decisions that depend on natural language understanding is still beyond our capabilities, partly since most of these tasks are very sparse and generating supervision signals for it does not scale.
I will discuss some of the challenges underlying reasoning – making natural language understanding decisions that depend on multiple, interdependent, models, and exemplify it using the domain of Reasoning about Time, as it is expressed in natural language.
While there exist a number of mechanically sophisticated exoskeletons, prostheses, and assistive robots, with articulations similar to those of the intact human arm and hand, these devices remain limited in their ability to augment human dexterity and safely interact with human users and collaborators. In particular, due to the limits of conventional sensing, robots remain […]
Emerging applications such as smart cities, autonomous vehicles, and mixed reality rely on embedded systems that are engaging with the physical environment through sensors. Building upon this connection, my vision is to advance Omnipresent Sensing by harnessing the wireless infrastructure in and around buildings and cities to act as a non-intrusive sensing platform. This is possible by […]
