Ziv Goldfeld, assistant professor of electrical and computer engineering, received a Computer and Information Science and Engineering (CISE) Research Initiation Initiative (CRII) award from the National Science Foundation for his project titled “New Paradigms in Generalization and Information-Theoretic Analysis of Deep Neural Networks.“
The project will study how information is processed in deep neural networks (DNNs) classifiers to make the decisions of AI mechanisms more transparent to end users and other stakeholders. The main objective is to shed light on the process by which DNNs progressively build representations, from crude and over-redundant representations in shallow layers, to highly-clustered and interpretable ones in deeper layers, and to give the designer more control over that process. Through rigorous performance guarantees, this project also aims to characterize the circumstances under which deep learning system are warranted not to fail. These advances will set the stage for the integration of high-performance AI systems in our daily lives, unlocking their invaluable societal impact.
The grant awards Goldfeld's team $175,000 over the next two years.
A research collaboration has found an efficient way to expand the collective behavior of swarming microrobots: Mixing different sizes of the micron-scale ‘bots enables them to self-organize into... Read more about Swarming microrobots self-organize into diverse patterns
The Graduate Diversity and Inclusion Awards recognized members of the graduate community for their accomplishments, leadership and commitments to advancing efforts around diversity, inclusion... Read more about Thirty-two receive awards recognizing inclusive excellence
Researchers in the School of Electrical and Computer Engineering are incorporating elements of physics, circuit design, photonics, systems architecture, information theory and other fields to make... Read more about Qubit control: Cornell engineers push to make quantum practical
