Adaptive quantum state tomography with neural networks

Current algorithms for quantum state tomography (QST) are costly both on the experimental front, requiring measurement of many copies of the state, and on the classical computational front, needing a long time to analyze the gathered data. Here, we introduce neural adaptive quantum state tomography (NAQT), a fast, flexible machine-learning-based algorithm for QST that adapts measurements and provides orders of magnitude faster processing while retaining state-of-the-art reconstruction accuracy. As in other adaptive QST schemes, measurement adaptation makes use of the information gathered from previous measured copies of the state to perform a targeted sensing of the next copy, maximizing the information gathered from that next copy. Our NAQT approach allows for a rapid and seamless integration of measurement adaptation and statistical inference, using a neural-network replacement of the standard Bayes’ update, to obtain the best estimate of the state. Our algorithm, which falls into the machine learning subfield of “meta-learning” (in effect “learning to learn” about quantum states), does not require any ansatz about the form of the state to be estimated. Despite this generality, it can be retrained within hours on a single laptop for a two-qubit situation, which suggests a feasible time-cost when extended to larger systems and potential speed-ups if provided with additional structure, such as a state ansatz.

Flexible Machine Learning based Cyberattack Detection using Spatiotemporal Patterns for Distribution Systems

The Article presents a versatile machine learning detection technique which is employed in distribution systems for cyberattacks considering spatiotemporal patterns. Spatiotemporal patterns are identified by the graph Laplacian which are supported on system-wide measurements. A versatile Bayes classifier is employed to coach spatiotemporal patterns which may well be compromised when cyberattacks happen. Cyberattacks are spotted by utilizing flexible Bayes classifier online.

Minimizing makespan of a flexible machine under tooling contraints

Computer Number Control (CNC) milling and lathe machines are widely used in manufacturing due to their flexibility in producing parts with a wide variety of geometries. Each flexible machine has a tool magazine capable of holding a set of tools. As machining requirements for each job change, tools can be removed and different ones can be inserted so that the next job can be processed. The existing literature on the job scheduling and the tool loading can be divided into four main areas. The first area is the tool loading for a pre-specified job sequence where the objective is to determine the optimal tool loading by minimizing the number of tool switching. In addition to tool loading, the second area also focuses on sequencing the jobs too; however, the objective is the same as the first one. Rather than to minimizing the number to tool switching, the focal point of the third area has been shifted to minimizing the makespan in presence of multiple process plans. However, the main assumption is that the magazine can hold all tools needed to process all jobs and tool switching is not required. The fourth area considers the geometric and mechanical properties of the tool, assuming a tool switching may be required due to tool life. The job scheduling and the tool loading literatures do not consider multiple process plans or tool life into their problem. Therefore, the first part of this thesis provides a Dynamic Programming method to determine the optimal makespan for a pre-specified sequence of jobs, assuming tool switching may required due to multiple process plans, the capacity of the tool magazine and due to the tool life. In the second part, the assumption for fixed job sequence is relaxed and a heuristic approach is used to first sequence the jobs and then Dynamic Programming is applied to find the optimal makespan for that particular job sequence.

Minimizing makespan of a flexible machine under tooling contraints

Computer Number Control (CNC) milling and lathe machines are widely used in manufacturing due to their flexibility in producing parts with a wide variety of geometries. Each flexible machine has a tool magazine capable of holding a set of tools. As machining requirements for each job change, tools can be removed and different ones can be inserted so that the next job can be processed. The existing literature on the job scheduling and the tool loading can be divided into four main areas. The first area is the tool loading for a pre-specified job sequence where the objective is to determine the optimal tool loading by minimizing the number of tool switching. In addition to tool loading, the second area also focuses on sequencing the jobs too; however, the objective is the same as the first one. Rather than to minimizing the number to tool switching, the focal point of the third area has been shifted to minimizing the makespan in presence of multiple process plans. However, the main assumption is that the magazine can hold all tools needed to process all jobs and tool switching is not required. The fourth area considers the geometric and mechanical properties of the tool, assuming a tool switching may be required due to tool life. The job scheduling and the tool loading literatures do not consider multiple process plans or tool life into their problem. Therefore, the first part of this thesis provides a Dynamic Programming method to determine the optimal makespan for a pre-specified sequence of jobs, assuming tool switching may required due to multiple process plans, the capacity of the tool magazine and due to the tool life. In the second part, the assumption for fixed job sequence is relaxed and a heuristic approach is used to first sequence the jobs and then Dynamic Programming is applied to find the optimal makespan for that particular job sequence.

Design and Fabrication of Portable spot-welding machine for sheet metal operation

Spot welding machine requires a lot of power, occupies large area and it is heavy to transport, restricted by height and does not weld all angle. On present work, we have tried to overcome the above problems by restructuring the design. Newly designed apparatus was simpler, lighter, portable, compact and flexible machine which will be able to weld at any angle and can be easily operated by even a non-skilled Labor with much ease and required accuracy. The first thing is the fabrication of the portable spot-welding machine which is divided into two phases, first is the formation of basic circuit of machine which includes small transformer of 1.2 kVA with output voltage 0 to 2.2 volt with 2.5-gauge wire & power switch and second is the formation of body and arm mechanism of the machine. For creating this machine, we used modelling software such as Autodesk Fusion 360 and created a prototype based on its design. In this project we made our own transformer according to requirements of specifications for welding as a general transformer used in electronic appliances was costly and as well a Bulky.

MLAir (v1.0) – a tool to enable fast and flexible machine learning on air data time series

With MLAir (Machine Learning on Air data) we created a software environment that simplifies and accelerates the exploration of new machine learning (ML) models, specifically shallow and deep neural networks, for the analysis and forecasting of meteorological and air quality time series. Thereby MLAir is not developed as an abstract workflow, but hand in hand with actual scientific questions. It thus addresses scientists with either a meteorological or an ML background. Due to their relative ease of use and spectacular results in other application areas, neural networks and other ML methods are also gaining enormous momentum in the weather and air quality research communities. Even though there are already many books and tutorials describing how to conduct an ML experiment, there are many stumbling blocks for a newcomer. In contrast, people familiar with ML concepts and technology often have difficulties understanding the nature of atmospheric data. With MLAir we have addressed a number of these pitfalls so that it becomes easier for scientists of both domains to rapidly start off their ML application. MLAir has been developed in such a way that it is easy to use and is designed from the very beginning as a stand-alone, fully functional experiment. Due to its flexible, modular code base, code modifications are easy and personal experiment schedules can be quickly derived. The package also includes a set of validation tools to facilitate the evaluation of ML results using standard meteorological statistics. MLAir can easily be ported onto different computing environments from desktop workstations to high-end supercomputers with or without graphics processing units (GPUs).

Efficient Reject Options for Particle Filter Object Tracking in Medical Applications

Reliable object tracking that is based on video data constitutes an important challenge in diverse areas, including, among others, assisted surgery. Particle filtering offers a state-of-the-art technology for this challenge. Becaise a particle filter is based on a probabilistic model, it provides explicit likelihood values; in theory, the question of whether an object is reliably tracked can be addressed based on these values, provided that the estimates are correct. In this contribution, we investigate the question of whether these likelihood values are suitable for deciding whether the tracked object has been lost. An immediate strategy uses a simple threshold value to reject settings with a likelihood that is too small. We show in an application from the medical domain—object tracking in assisted surgery in the domain of Robotic Osteotomies—that this simple threshold strategy does not provide a reliable reject option for object tracking, in particular if different settings are considered. However, it is possible to develop reliable and flexible machine learning models that predict a reject based on diverse quantities that are computed by the particle filter. Modeling the task in the form of a regression enables a flexible handling of different demands on the tracking accuracy; modeling the challenge as an ensemble of classification tasks yet surpasses the results, while offering the same flexibility.

Evidence of Inflated Prediction Performance: A Commentary on Machine Learning and Suicide Research

The use of machine learning is increasing in clinical psychology, yet it is unclear whether these approaches enhance the prediction of clinical outcomes. Several studies show that machine-learning algorithms outperform traditional linear models. However, many studies that have found such an advantage use the same algorithm, random forests with the optimism-corrected bootstrap, for internal validation. Through both a simulation and empirical example, we demonstrate that the pairing of nonlinear, flexible machine-learning approaches, such as random forests with the optimism-corrected bootstrap, provide highly inflated prediction estimates. We find no advantage for properly validated machine-learning models over linear models.

Basic design of a new multicomponent standard machine and proposal for a definition of the nominal loads

The increasing demand in industry for calibrated multicomponent measuring, especially with mixed loads, supports the necessary development for the next level of Multicomponent Standard Machines. Our next step is a flexible machine, which ensures an automatic force and moment generation for realistic load situations. The multicomponent measuring in realistic load situations improves test results, assures comparability to application and reduces time expenses in calibration. This paper deals with definition of the capacity of the main components of the new machine type and its possibilities for realistic applications.

ATRT-33. ENABLING RAPID CLASSIFICATION OF ATRT WITH NANOSTRING NCOUNTER PLATFORM

In recent years, using gene expression and methylation array platform, multiple research groups have reported the presence of at least three major Atypical Teratoid Rhabdoid Tumor (ATRT) subtypes that exhibit distinct epigenetic, transcriptomic and clinical features. Yet, utilizing ATRT subtypes in a clinical setting remains challenging due to a lack of suitable biological markers, limited sample quantities and relatively high cost of current assays. To address this gap between research and clinical practice, we have designed an assay that utilizes a custom 35 signature genes panel for the NanoString nCounter System and have created a flexible machine learning classifier package for ATRT tumour subtyping. We have analyzed 71 ATRT primary tumours with matching gene expression data using the 35 genes panel. 60% of the data was used for models training (10 repeats of 10-fold cross validation with subgroup balanced sample splitting) resulting in overall 94.6% training accuracy. The remaining 40% of the samples were used for model validation and the assay was able to achieve 92–100% accuracy with no subgroup bias. To demonstrate the flexibility of the workflow, we have tested it against other transcriptome-based methods such as gene expression array and RNASeq. We have also demonstrated its use in samples that were not classifiable by methylation-based method. We are presenting here a rapid and accurate ATRT subtyping assay for clinical usage that is compatible with archived ATRT tissues.