<< Wednesday, April 24, 2019 >>

Wednesday, April 24, 2019

Scientific Computing and Matrix Computations Seminar: Analysis of a Two-Layer Neural Network via Displacement Convexity

Seminar: Scientific Computing: CS | April 24 | 2-3 p.m. | 380 Soda Hall

 Marco Mondelli, Stanford U.

 Electrical Engineering and Computer Sciences (EECS)

Fitting a function by using linear combinations of a large number N of
"simple" components is one of the most fruitful ideas in statistical
learning. This idea lies at the core of a variety of methods, from
two-layer neural networks to kernel regression, to boosting. In
general, the resulting risk minimization problem is nonconvex and is
solved by gradient descent or its variants....   More >

A Convex Duality Framework for GANs: BLISS Seminar

Seminar: EE: Berkeley Laboratory for Information and System Sciences (BLISS) | April 24 | 2-3 p.m. | 531 Cory Hall

 Farzan Farnia, Stanford

 Electrical Engineering and Computer Sciences (EECS)

Generative adversarial network (GAN) is a minimax game between a generator mimicking the true model and a discriminator distinguishing the samples produced by the generator from the real training samples. Given a discriminator trained over the entire space of functions, this game reduces to finding the generative model which minimizes a divergence score, e.g. the Jensen-Shannon (JS) divergence,...   More >

EECS Colloquium: Memcomputing: leveraging memory and physics to compute efficiently

Colloquium: Departmental: EE: CS | April 24 | 4-5 p.m. | Soda Hall, 306 (HP Auditorium)

 Massimiliano Di Ventra, University of California, San Diego

 Electrical Engineering and Computer Sciences (EECS)

It is well known that physical phenomena may be of great help in computing some difficult problems efficiently. A typical example is prime factorization that may be solved in polynomial time by exploiting quantum entanglement on a quantum computer. There are, however, other types of (non-quantum) physical properties that one may leverage to compute efficiently a wide range of hard problems. In...   More >

Cybersecurity and Defense: Trends, Challenges, and Careers

Panel Discussion: EE: CS | April 24 | 6-8 p.m. | Soda Hall, HP Auditorium

 Chris Jay Hoofnagle, UC Berkeley School of Law and School of Information; Nicholas Weaver, UC Berkeley International Computer Science Institute; Lt. Col. Kevin Childs, Hoover Institution, US Air Force; Dorothy Ngutter, US Department of State

 Delta Phi Epsilon, UC Berkeley Institute of Electrical and Electronics Engineers, Policy Review at Berkeley, Kappa Alpha Pi Pre-Law Fraternity, Review of International Conflict and Security

Join us for a discussion with four distinguished panelists about trends, challenges, and career opportunities for students interested in cybersecurity and defense. Historically, industry knowledge and career paths for students interested in tech and tech-policy have been most pronounced in the private sector, in spite of emerging public sector needs for national security roles in tech. Our panel...   More >