With the explosive growth of the smart society and Internet of Things, enormous amounts of information are available in the enhanced world around us and the cyber-world beyond. Hence the traditional human input/output modalities (sight, smell, hearing, taste and touch as inputs, and motor control as output) no longer have the necessary bandwidth or expressiveness to effectively deal with...

Dexter Scobee's Dissertation talk on "Approaches to Safety in Inverse Reinforcement Learning"

The enormous decrease in the cost of genomic sequencing over the past two decades has enabled researchers to revisit previously unaddressable questions in sequence analysis. However, this boom of genomic information has introduced new sets of problems that often demand computationally efficient methods. In this talk, we describe computational tools for two such settings involving...

Many California residential electric customers are transitioning to Time-of-Use (TOU) rate plans as part of statewide efforts to create a smarter energy future and healthier environment while balancing the need to keep customer rates affordable. PG&E will soon transition eligible customers from their standard tiered rate plan to the new “Time-of-Use Peak Pricing 4-9p.m. Every Day”. Learn more...

Title: Topics in Cancer Genomics Abstract: My talk will focus on how to leverage thousands of cancer genomes and functional genomics datasets to discover disease-associated regulators and variations. First, I will go over the ENCODE annotation related to the cancer genome. I will show how extended gene annotation allows us to place oncogenic transformations in the context of a large cell...

Full details about this meeting will be posted here: https://bids.berkeley.edu/events.

Autonomous driving has attracted a lot of attention in the past few years. A typical self-driving system needs manual design and coordination across multiple modules, such as perception, behavior prediction, planning and trajectory generation. Those manually designed information flow might be far from optimal. Deep learning has dramatically improved image recognition performance by replacing the...

TBA

TBA

TBA