We extract pixel-level masks of extreme weather patterns using variants of Tiramisu and DeepLabv3+ neural networks. We describe improvements to the software frameworks, input pipeline, and the network training algorithms necessary to efficiently scale deep learning on the Piz Daint and Summit systems. The Tiramisu network scales to 5300 P100 GPUs with a sustained throughput of 21.0 PF/s and parallel efficiency of 79.0%. DeepLabv3+ scales up to 27360 V100 GPUs with a sustained throughput of 325.8 PF/s and a parallel efficiency of 90.7% in single precision. By taking advantage of the FP16 Tensor Cores, a half-precision version of the DeepLabv3+ network achieves a peak and sustained throughput of 1.13 EF/s and 999.0 PF/s respectively.

Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to effectively leverage tactile sensing as well as accurate physics models of contacts and forces remain largely elusive, and it is unclear how to even specify a desired behavior in terms of tactile percepts. In this paper, we take a step towards addressing these issues by combining high-resolution tactile sensing with data-driven modeling using deep neural network dynamics models. We propose deep tactile MPC, a framework for learning to perform tactile servoing from raw tactile sensor inputs, without manual supervision. We show that this method enables a robot equipped with a GelSight-style tactile sensor to manipulate a ball, analog stick, and 20-sided die, learning from unsupervised autonomous interaction and then using the learned tactile predictive model to reposition each object to user-specified configurations, indicated by a goal tactile reading. Videos, visualizations and the code are available here: https://sites.google.com/view/deeptactilempcEqual contribution

Abstract. Identifying, detecting, and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection, and segmentation (i.e., pixel-level classification) have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of deep learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning – when labeled datasets are readily available. Reliable labeled training data for extreme weather and climate events is scarce. We create “ClimateNet” – an open, community-sourced human-expert-labeled curated dataset that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification – i.e., segmentation – of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs, or “the background” at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, high-fidelity, and highly precise analytics of climate data using a curated expert-labeled dataset – ClimateNet. ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns and applied to observational and reanalysis data products via transfer learning.

Abstract. Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-theart techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. We will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.

Background: Meditation is gaining recognition as a tool to impact health and well-being. Samyama is an 8-day intensive residential meditation experience conducted by Isha Foundation requiring several months of extensive preparation and vegan diet. The health effects of Samyama have not been previously studied. The objective was to assess physical and emotional well-being before and after Samyama participation by evaluating psychological surveys and objective health biomarkers.Methods: This was an observational study of 632 adults before and after the Isha Samyama retreat. All participants were invited to complete surveys. Controls included household significant others. Surveys were completed at baseline (T1), just before Samyama (T2), immediately after Samyama (T3), and 3 months later (T4) to assess anxiety, depression, mindfulness, joy, vitality, and resilience through validated psychometric scales. Voluntary blood sampling for biomarker analysis was done to assess hemoglobin (Hb), HbA1c, lipid profile, and C-reactive protein (CRP). Primary outcomes were changes in psychometric scores, body weight, and blood biomarkers.Results: Depression and anxiety scores decreased from T1 to T3, with the effect most pronounced in participants with baseline depression or anxiety. Scores at T4 remained below baseline for those with pre-existing depression or anxiety. Vitality, resilience, joy, and mindfulness increased from T1 to T3 (sustained at T4). Body weight decreased by 3% from T1 to T3. Triglycerides (TG) were lower from T2 to T3. Participants had lower HbA1c and HDL at T2, and lower CRP at all timepoints compared with controls.Conclusions: Participation in the Isha Samyama program led to multiple benefits. The 2-month preparation reduced anxiety, and participants maintained lower anxiety levels at 3 months post-retreat. Physical health improved over the course of the program as evidenced by weight loss and improved HbA1C and lipid profile. Practices associated with the Samyama preparation phase and the retreat may serve as an effective way to improve physical and mental health. Future studies may examine their use as an alternative therapy in patients with depression and/or anxiety.Clinical Trial Registration:www.ClinicalTrials.gov, Identifier: 1801728792. Registered retrospectively on 4/17/2020.