In order to operate in and interact with the physical world, robots need to have estimates of the current and future state of the environment. We thus equip robots with sensors and build models and algorithms that, given some measurements, produce estimates of the current or future states. Environments can be unpredictable and sensors are not perfect. Therefore, it is important to both use all information available, and to do so optimally: making sure that we get the best possible answer from the amount of information we have. However, in prevalent research, uncommon sensors, such as sound or radio-frequency signals, are commonly ignored for state estimation; and the most popular solvers employed to produce state estimates are only of local nature, meaning they may produce suboptimal estimates for the typically non-convex estimation problems. My research aims to use resources more optimally, by building on 1) multi-modality: using ubiquitous RF transceivers and microphones to support state estimation, 2) building certifiably optimal solvers and 3) learning and improving adequate models from data.

One of the key design choices of any sampling calorimeter is how fine to make the longitudinal and transverse segmentation. To inform this choice, we study the impact of calorimeter segmentation on energy reconstruction. To ensure that the trends are due entirely to hardware and not to a sub-optimal use of segmentation, we deploy deep neural networks to perform the reconstruction. These networks make use of all available information by representing the calorimeter as a point cloud. To demonstrate our approach, we simulate a detector similar to the forward calorimeter system intended for use in the ePIC detector, which will operate at the upcoming Electron Ion Collider. We find that for the energy estimation of isolated charged pion showers, relatively fine longitudinal segmentation is key to achieving an energy resolution that is better than 10% across the full phase space. These results provide a valuable benchmark for ongoing EIC detector optimizations and may also inform future studies involving high-granularity calorimeters in other experiments at various facilities.

This paper presents a variation of the back-propagation algo(cid:173) rithm that makes optimal use of a network hidden units by de(cid:173) cr asing an "energy" term written as a function of the squared activations of these hidden units. The algorithm can automati(cid:173) cally find optimal or nearly optimal architectures necessary to solve known Boolean functions, facilitate the interpretation of the activation of the remaining hidden units and automatically estimate the complexity of architectures appropriate for phonetic labeling problems. The general principle of the algorithm can also be adapted to different tasks: for example, it can be used to eliminate the [0, 0] local minimum of the [-1.

A new crop of data preparation tools, powered by machine learning, are changing the way that businesses prepare their data for optimal use. Here's what you need to know. At analytics-capable companies, just about every business department is asking for more data to help them make better decisions. But many of these same companies are also struggling with one common problem: It simply takes too long to transform raw data into meaningful sets that analysts, data scientists, and business users can actually use to their advantage In fact, according to a report from Forrester, 59 percent of these decision-makers say that data prep is the key bottleneck they must over to achieve better business intelligence through analytics. One of the primary problems is that data preparation is a time-consuming, often-manual process that relies heavily on human labor.