The Center for Advanced Mathematics for Energy Research Applications (CAMERA)  is an integrated, cross-disciplinary center aimed at inventing, developing, and delivering the fundamental new mathematics required to capitalize on experimental investigations at scientific facilities.  

Open Positions:

CAMERA has several openings at the career scientist, postdoc, and engineering levels. All are focused on combining state-of-the-art mathematics, new algorithms, and efficient and robust software implementations to meet the needs of DOE facilities, particularly at the light sources.

For information about current openings, please go here

CAMERA Workshop Tackles Tomographic Reconstruction

November 29, 2016

CAMERA—the Center for Advanced Mathematics for Energy Research Applications at Lawrence Berkeley National Laboratory—hosted a workshop November 9-11 in Berkeley Lab’s Shyh Wang Hall to highlight the state-of-the-art in tomographic reconstruction algorithms and software for synchrotrons, and to discuss future goals and collaborations.

The workshop brought together users, practitioners and developers of this software to assess the current landscape of available algorithms, investigate commonalities and differences among the various techniques and discuss a range of related topics, from required theoretical and algorithmic advancements on through to practical issues of implementation and deployment. Over 40 people attended, representing six different countries and eleven different light sources.

 

CAMERA Introduces "SlideCAM": Minimalist Machine Learning” that analyzes images from very little information

Feb 20, 2018

CAMERA—the Center for Advanced Mathematics for Energy Research Applications at Lawrence Berkeley National Laboratory, has introduced “Minimalist Machine Learning” that analyzes images from very little information. CAMERA researchers Daniel Pelt and James Sethian have developed highly efficient "Mixed-Scale Dense" convolution neural networks tailored for analyzing experimental scientific images from limited training data.

 

Rather than relying on the tens or hundreds of thousands of images used by typical machine learning methods, this new approach “learns” much more quickly and requires far fewer images.  CAMERA's approach is already being used to extract biological structure

from cell images, and is poised to provide a major new computational tool to analyze data across a wide range of research areas.

 

The underlying mathematics appeared in an article in the Proceedings of the National Academy of Sciences from cell images, and is poised to provide a major new computational tool to analyze data across a wide range of research areas.

To make the algorithm accessible to a wide set of researchers, a Berkeley team led by Olivia Jain and Simon Mo built a web portal “Segmenting Labeled Image Data Engine (SlideCAM)” as part of the CAMERA suite of tools for DOE experimental facilities. Users may remotely execute CAMERA's algorithms by visiting slidecam-camera.lbl.gov.

For more details, see

            (1) Minimalist Machine Learning (Press Release)

            (2) Link to publication

            (3) Link to Slidecam web site.