Language models trained with Maximum Likelihood Estimation (MLE) have been considered as a mainstream solution in Natural Language Generation (NLG) for years. Recently, various approaches with Generative Adversarial Nets (GANs) have also been proposed. While offering exciting new prospects, GANs in NLG by far are nevertheless reportedly suffering from training instability and mode collapse, and therefore outperformed by conventional MLE models. In this work, we propose techniques for improving GANs in NLG, namely Best Student Forcing (BSF), a novel yet simple adversarial training mechanism in which generated sequences of high quality are selected as temporary ground-truth to further train the generator. We also use an ensemble of discriminators to increase training stability and sample diversity. Evaluation shows that the combination of BSF and multiple discriminators consistently performs better than previous GAN approaches over various metrics, and outperforms a baseline MLE in terms of Fr ́ech ́et Distance, a recently proposed metric capturing both sample quality and diversity.

RainCube (Radar in a CubeSat) is a technology demonstration mission to enable Ka-band precipitation radar technologies on a low-cost, quick-turnaround platform. The 6U CubeSat currently in orbit features a radar payload built by the Jet Propulsion Laboratory (JPL) and a spacecraft bus and operations provided by Tyvak Nano-Satellite Systems. Following the deployment of the half-meter parabolic antenna, the radar first observed rainfall over Mexico. The mission continues to operate and has met all requirements through repeated observations of precipitation in the atmosphere. RainCube is funded through the Science Mission Directorate's (SMD) Research Opportunities in Space and Earth Science (ROSES) 2015 In-Space Validation of Earth Science Technologies (InVEST) solicitation with the goal of raising the instrument TRL to 7.

Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised learning tasks such as object classification and semantic segmentation. While massive point cloud datasets can be captured using modern scanning technology, manually labelling such large 3D point clouds for supervised learning tasks is a cumbersome process. This necessitates methods that can learn from unlabelled data to significantly reduce the number of annotated samples needed in supervised learning. We propose a self-supervised learning task for deep learning on raw point cloud data in which a neural network is trained to reconstruct point clouds whose parts have been randomly rearranged. While solving this task, representations that capture semantic properties of the point cloud are learned. Our method is agnostic of network architecture and outperforms current unsupervised learning approaches in downstream object classification tasks. We show experimentally, that pre-training with our method before supervised training improves the performance of state-of-the-art models and significantly improves sample efficiency.

RainCube (Radar in a CubeSat) is a technology demonstration mission to enable Ka-band precipitation radar technologies on a low-cost, quick-turnaround platform. The mission is manifested for an ISS deployment with the ELaNa-23 launch, currently scheduled in May, 2018. Radar instruments have often been regarded as unsuitable for small satellite platforms due to their traditionally large size, weight, and power. The Jet Propulsion Laboratory (JPL) has developed a novel architecture compatible with the 6U class. The RainCube mission will validate two key technologies in the space environment - a miniaturized Ka-band precipitation profiling radar that occupies ~ 2.5U and a 0.5m Ka-band deployable parabolic antenna stowed within 1.5U. The spacecraft bus is developed by Tyvak Nanosatellite Systems, who will be responsible for integration of the flight system and mission operations. RainCube is funded through the Science Mission Directorate's (SMD) Research Opportunities in Space and Earth Science (ROSES) 2015 In-Space Validation of Earth Science Technologies (InVEST) solicitation with the goal of raising the instrument TRL to 7.