Probabilistic inference is the problem of estimating the hidden variables (states or parameters) of a system in an optimal and consistent fashion as a set of noisy or incomplete observations of the system becomes available online. The optimal solution to this problem is given by the recursive Bayesian estimation algorithm which recursively updates the posterior density of the system state as new observations arrive. This posterior density constitutes the complete solution to the probabilistic inference problem, and allows us to calculate any “optimal” estimate of the state. Unfortunately, for most real-world problems, the optimal Bayesian recursion is intractable and approximate solutions must be used. Within the space of approximate solutions, the extended Kalman filter (EKF) has become one of the most widely used algorithms with applications in state, parameter and dual estimation. Unfortunately, the EKF is based on a sub-optimal implementation of the recursive Bayesian estimation framework applied to Gaussian random variables. This can seriously affect the accuracy or even lead to divergence of any inference system that is based on the EKF or that uses the EKF as a component part. Recently a number of related novel, more accurate and theoretically better motivated algorithmic alternatives to the EKF have surfaced in the literature, with specific application to state estimation for automatic control. We have extended these algorithms, all based on derivativeless deterministic sampling based approximations of the relevant Gaussian statistics, to a family of algorithms called Sigma-Point Kalman Filters (SPKF). Furthermore, we successfully expanded the use of this group of algorithms (SPKFs) within the general field of probabilistic inference and machine learning, both as stand-alone filters and as subcomponents of more powerful sequential Monte Carlo methods (particle filters). We have consistently shown that there are large performance benefits to be gained by applying Sigma-Point Kalman filters to areas where EKFs have been used as the de facto standard in the past, as well as in new areas where the use of the EKF is impossible.

/pdf/sigma-point-kalman-filters-for-probabilistic-inference-in-1affrc62j6.pdf

Sigma-point kalman filters for probabilistic inference in dynamic state-space models

https://superfund.berkeley.edu/pdf/92.pdf

Epidemiology of Myelodysplastic Syndromes and Chronic Myeloproliferative Disorders in the United States, 2001-2004, Using Data From the NAACCR and SEER Programs

Diagnosis and treatment of primary myelodysplastic syndromes in adults: recommendations from the European LeukemiaNet

Monads have become very popular for structuring functional programs since Wadler introduced their use in 1990. In particular, libraries of combinators are often based on a monadic type. Such libraries share (in part) a common interface, from which numerous benefits flow, such as the possibility to write generic code which works together with any library. But, several interesting and useful libraries are fundamentally incompatible with the monadic interface. In this paper I propose a generalisation of monads, which I call arrows, with significantly wider applicability. The paper shows how many of the techniques of monadic programming generalise to the new setting, and gives examples to show that the greater generality is useful. In particular, three non-monadic libraries for efficient parsing, building graphical user interfaces, and programming active web pages fit naturally into the new framework.

Generalising monads to arrows

A probabilistic framework, called Sigma-point Kalman Filters (SPKF) was applied to the problem domain addressed by the extended Kalman Filter (EKF). SPKF methods are superior to the standard EKF based estimation approaches, as an SPKF achieves second-order or higher accuracy. The SPKF has also been applied to the integrated navigation problem as it relates to unmanned aerial vehicle (UAV) autonomy. The SPKF-based sensor latency compensation technique is used to demonstrate the lagged GPS measurements.

/pdf/sigma-point-kalman-filters-for-nonlinear-estimation-and-3h5o0hche0.pdf

Sigma-Point Kalman Filters for Nonlinear Estimation and Sensor Fusion: Applications to Integrated Navigation

Cortical Evoked Potentials Obtained After Stimulation of the Lower Urinary Tract

In this paper we present a method for optimal control of a nonlinear highly realistic helicopter model based on a combination of a neural network (NN) feedback controller and a state-dependen t Riccati equation (SDRE) controller. Optimization of the NN is performed within a receding horizon model predictive control (MPC) framework, subject to dynamic and kinematic constraints. The SDRE controller utilizes a simplified 6DOF rigid body dynamic model, and augments the NN controller by providing an initial feasible solution and improving stability. While the SDRE control provides robustness based on a pseudo-linear formulation of the dynamics, the MPNC utilizes the highly accurate numerical helicopter model.

Model predictive neural control of a high-fidelity helicopter model.

Programming with Fudgets

In this paper we argue that a programming language for real-time systems should support the declaration of time-constraints, and that those constraints should attach to a welldeveloped notion of re ...

Programming with time-constrained reactions

Cryptol is a programming language designed for specifying cryptographic algorithms. Despite its high-level modeling nature, Cryptol programs are fully executable. Further, a large subset of Cryptol can be automatically synthesized to hardware. To meet the inherent high-assurance requirements of cryptographic systems, Cryptol comes with a suite of formal-methods based tools that enable users to perform various program verification tasks. In this paper, we provide an overview of Cryptol and its verification toolset, especially focusing on the co-verification of third-party VHDL implementations against highlevel Cryptol specifications. As a case study, we demonstrate the technique on two hand-written VHDL implementations of the Skein hash algorithm.

Magnus Carlsson

Papers

Cortical Evoked Potentials Obtained After Stimulation of the Lower Urinary Tract

Model predictive neural control of a high-fidelity helicopter model.

Programming with Fudgets

Programming with time-constrained reactions

Hardware/software co-verification of cryptographic algorithms using Cryptol