There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Three parallel algorithms for classical molecular dynamics are presented. The first assigns each processor a fixed subset of atoms; the second assigns each a fixed subset of inter-atomic forces to compute; the third assigns each a fixed spatial region. The algorithms are suitable for molecular dynamics models which can be difficult to parallelize efficiently—those with short-range forces where the neighbors of each atom change rapidly. They can be implemented on any distributed-memory parallel machine which allows for message-passing of data between independently executing processors. The algorithms are tested on a standard Lennard-Jones benchmark problem for system sizes ranging from 500 to 100,000,000 atoms on several parallel supercomputers--the nCUBE 2, Intel iPSC/860 and Paragon, and Cray T3D. Comparing the results to the fastest reported vectorized Cray Y-MP and C90 algorithm shows that the current generation of parallel machines is competitive with conventional vector supercomputers even for small problems. For large problems, the spatial algorithm achieves parallel efficiencies of 90% and a 1840-node Intel Paragon performs up to 165 faster than a single Cray C9O processor. Trade-offs between the three algorithms and guidelines for adapting them to more complex molecular dynamics simulations are also discussed.

Fast parallel algorithms for short-range molecular dynamics

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Soil Chemical Analysis

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

This article presents the development and application of a fault-tolerant control technology, its online implementation, and results from several tests conducted for a large-sized HVAC system. By integrating model-based model predictive control and data-driven fault detection and diagnosis algorithms, the technology automatically adapts the HVAC control laws to a set of subsystem faults and can therefore reach and maintain the largest energy consumption reduction levels that are achievable at any point throughout a building lifecycle. The model predictive control algorithm generates optimal set-points that minimize energy consumption for the HVAC actuator loops while meeting equipment operational constraints and occupant thermal comfort constraints. The fault detection and diagnosis algorithm uses probabilistic graphical models to detect and classify in real time potential faults of the HVAC actuators based on data from multiple sensors. The fault-tolerant control system is realized by executing the two a...

Fault-tolerant optimal control of a building HVAC system

Robustness of Deep Reinforcement Learning (DRL) algorithms towards adversarial attacks in real world applications such as those deployed in cyber-physical systems (CPS) are of increasing concern. Numerous studies have investigated the mechanisms of attacks on the RL agent's state space. Nonetheless, attacks on the RL agent's action space (corresponding to actuators in engineering systems) are equally perverse, but such attacks are relatively less studied in the ML literature. In this work, we first frame the problem as an optimization problem of minimizing the cumulative reward of an RL agent with decoupled constraints as the budget of attack. We propose the white-box Myopic Action Space (MAS) attack algorithm that distributes the attacks across the action space dimensions. Next, we reformulate the optimization problem above with the same objective function, but with a temporally coupled constraint on the attack budget to take into account the approximated dynamics of the agent. This leads to the white-box Look-ahead Action Space (LAS) attack algorithm that distributes the attacks across the action and temporal dimensions. Our results showed that using the same amount of resources, the LAS attack deteriorates the agent's performance significantly more than the MAS attack. This reveals the possibility that with limited resource, an adversary can utilize the agent's dynamics to malevolently craft attacks that causes the agent to fail. Additionally, we leverage these attack strategies as a possible tool to gain insights on the potential vulnerabilities of DRL agents.

/pdf/spatiotemporally-constrained-action-space-attacks-on-deep-3ntydlphzb.pdf

Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents

Unmanned aircraft system (UAS) is a particularly powerful tool for plant phenotyping, due to reasonable cost of procurement and deployment, ease and flexibility for control and operation, ability to reconfigure sensor payloads to diversify sensing, and the ability to seamlessly fit into a larger connected phenotyping network. These advantages have expanded the use of UAS-based plant phenotyping approach in research and breeding applications. This paper reviews the state of the art in the deployment, collection, curation, storage, and analysis of data from UAS-based phenotyping platforms. We discuss pressing technical challenges, identify future trends in UAS-based phenotyping that the plant research community should be aware of, and pinpoint key plant science and agronomic questions that can be resolved with the next generation of UAS-based imaging modalities and associated data analysis pipelines. This review provides a broad account of the state of the art in UAS-based phenotyping to reduce the barrier to entry to plant science practitioners interested in deploying this imaging modality for phenotyping in plant breeding and research areas.

/pdf/uas-based-plant-phenotyping-for-research-and-breeding-g941lxbuz4.pdf

UAS-Based Plant Phenotyping for Research and Breeding Applications.

Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement learning (DRL) have demonstrated its benefits in a large variety of data-driven decisions and control applications. As reliance on ML-enabled systems grows, it is imperative to study the performance of these systems under malicious state and actuator attacks. Traditional control systems employ resilient/fault-tolerant controllers that counter these attacks by correcting the system via error observations. However, in some applications, a resilient controller may not be sufficient to avoid a catastrophic failure. Ideally, a robust approach is more useful in these scenarios where a system is inherently robust (by design) to adversarial attacks. While robust control has a long history of development, robust ML is an emerging research area that has already demonstrated its relevance and urgency. However, the majority of robust ML research has focused on perception tasks and not on decision and control tasks, although the ML (specifically RL) models used for control applications are equally vulnerable to adversarial attacks. In this paper, we show that a well-performing DRL agent that is initially susceptible to action space perturbations (e.g. actuator attacks) can be robustified against similar perturbations through adversarial training.

Robustifying Reinforcement Learning Agents via Action Space Adversarial Training

The first part of this two-part paper, which is a companion paper, has developed a novel concept of fault detection and isolation (FDI) in aircraft gas turbine engines. The FDI algorithms are built upon the statistical pattern recognition method of symbolic dynamic filtering (SDF) that is especially suited for real-time detection and isolation of slowly evolving anomalies in engine components, in addition to abrupt faults. The FDI methodology is based on the analysis of time series data of available sensors and/or analytically derived variables in the gas path dynamics. The current paper, which is the second of two parts, validates the algorithms of FDI, formulated in the first part, on a simulation test bed. The test bed is built upon an integrated model of a generic two-spool turbofan aircraft gas turbine engine including the engine control system.

https://mne.psu.edu/ray/journalasokray/2008/188sarkaryasar08part02.pdf

Soumik Sarkar

Papers

Fault-tolerant optimal control of a building HVAC system

Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents

UAS-Based Plant Phenotyping for Research and Breeding Applications.

Robustifying Reinforcement Learning Agents via Action Space Adversarial Training

Fault detection and isolation in aircraft gas turbine engines. Part 2: Validation on a simulation test bed