A machine learning decision criterion for reducing scan time for hyperspectral neutron computed tomography systems.

We present the first machine learning-based autonomous hyperspectral neutron computed tomography experiment performed at the Spallation Neutron Source. Hyperspectral neutron computed tomography allows the characterization of samples by enabling the reconstruction of crystallographic information and elemental/isotopic composition of objects relevant to materials science. High quality reconstructions using traditional algorithms such as the filtered back projection require a high signal-to-noise ratio across a wide wavelength range combined with a large number of projections.

MICA-G129R: A bifunctional fusion protein increases PRLR-positive breast cancer cell death in co-culture with natural killer cells.

Breast cancer cells were reported to up-regulate human prolactin receptor (PRLR) to assist their growth through the utilization of prolactin (PRL) as the growth factor, which makes PRLR a potential therapeutic target for breast cancer. On the other hand, advanced cancer cells tend to down-regulate or shed off stress signal proteins to evade immune surveillance and elimination. In this report, we created a fusion protein consisting of the extracellular domain of MHC class I chain-related protein (MICA), a stress signal protein and ligand of the activating receptor NKG2D of natural killer (NK) cells, and G129R, an antagonistic variant of PRL.

Multiagent Consensus Equilibrium in Molecular Structure Determination.

Multiagent consensus equilibrium (MACE) is demonstrated for the integration of experimental observables as constraints in molecular structure determination and for the systematic merging of multiple computational architectures. MACE is founded on simultaneously determining the equilibrium point between multiple experimental and/or computational agents; the returned state description (e.g.

Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation.

We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics. We employ the kernelized Lipschitz estimation to learn multiplier matrices that are used in semidefinite programming frameworks for computing admissible initial control policies with provably high probability. Such admissible controllers enable safe initialization and constraint enforcement while providing exponential stability of the equilibrium of the closed-loop system.