A New Approach to Linear Filtering and Prediction Problems

2002

Subfields: Signal Processing

Citations in the corpus

• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review (2018, background): “1 Frameworks for Control as Inference Framing control, decision making, and reinforcement learning as a probabilistic inference and learning problem has a long history, going back to original work by Rudolf Kalman (Kalman, 1960), who described how the Kalman smoothing algorithm can also be used to s”
• Optimization Methods for Large-Scale Machine Learning (2016, methodology): “lopments in the eld of machine learning. The SG method was rst proposed in [130], not as a gradient method, but as a Markov chain. Viewed more broadly, the works by Robbins and Monro [130] and Kalman [83] mark the beginning of the eld of stochastic approximation, which studies the behavior of iterat”
• Deep learning in neural networks: An overview (2014, background): “A combination of a decoupled extended Kalman filter (Feldkamp, Prokhorov, Eagen, & Yuan, 1998; Feldkamp, Prokhorov, & Feldkamp, 2003; Haykin, 2001; Kalman, 1960; Puskorius & Feldkamp, 1994; Williams, 1992b) and an LSTM RNN (Pérez-Ortiz et al., 2003) learned to deal correctly with values of n up to…”
• Deep Kalman Filters (2015, methodology): “We show that recent techniques in variational inference [15, 10] can be adopted to learn a broad set of Kalman Filters [8] with a single algorithm.”
• Filtering with State-Observation Examples via Kernel Monte Carlo Filter (2013, background): “The simplest form is a linear-gaussian state-space model, which enables analytic computation of the posteriors; this is the principle of the classical Kalman filter (Kalman, 1960).”
• Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction (2019, methodology): “For many filter models – such as the Kalman filter (Kalman, 1960) and non-linear variants like the unscented Kalman filter (Julier & Uhlmann, 1997) – deterministic functions are used at each step to adjust the sufficient statistics of the belief state, guided by generative models of the data.”
• Financial Time Series Prediction Using Deep Learning (2017, methodology): “The Kalman Filter [1] and Auto-Regressive (AR) Models are seminal statistical approaches, where the ARMA [2] and ARIMA [3] (Auto-Regressive Integrated Moving Average) models are further generalizations of the AR, derived by combining the AR models with the moving-average (MA) models.”
• Asymmetric Actor Critic for Image-Based Robot Learning (2017, background): “One option is to infer the full state by visual detectors [13], [14] or state prediction filters [15].”
• Dream to Control: Learning Behaviors by Latent Imagination (2019, methodology): “The model mimics a non-linear Kalman filter (Kalman, 1960), latent state space model, or HMM with real-valued states.”
• WRITING MEMORIES WITH LIGHT-ADDRESSABLE REINFORCEMENT CIRCUITRY (2009, background): “Engineers (Kalman, 1960), researchers in machine learning (Samuel, 1959; Holland, 1986; Sutton and Barto, 1998), and psychologists (Rescorla and Wagner, 1972) have developed models of adaptive behavior in which error signals play a central role; they have also designed efficient algorithms for their”
• Covariance Estimation: The GLM and Regularization Perspectives (2011, methodology): “Some of the more explicit uses are in Kalman (1960) for filtering of state-space models and the Gaussian graphical models (Wermuth, 1980).”
• Data Assimilation: A Mathematical Introduction (2015, background): “The idea behind the Kalman filter, to optimally combine model and data, is arguably one of the most important ideas in applied mathematics over the last century: the impact of the paper [65] on many applications domains has been huge.”
• Automatic detection of oestrus and health disorders using data from electronic sow feeders (2008, methodology): “The DLM combined with a Kalman Filter (KF) (Kalman, 1960) estimates the underlying state vector θt by its mean vector mt and its variance–covariance matrix Ct (the model variance) given all previous observations O1,.”
• Marginalized particle filters for mixed linear/nonlinear state-space models (2005, methodology): “Using Bayes' theorem we can then marginalize out the linear state variables from (1) and estimate them using the Kalman filter [22], which is the optimal filter for this case.”
• Modeling Ordered Choices: A Primer and Recent Developments (2008, unknown): “Walker and Duncan were in similar territory, but they relied on a weighted least squares procedure and an algorithm based on a Kalman filter [Kalman (1960)] that has not reappeared in the literature.”
• An Open Approach to Autonomous Vehicles (2015, methodology): “Kalman Filters is used under a linear assumption that our autonomous vehicle is driving at constant velocity while tracking moving objects.(6) Its computational cost is lightweight and suited for real-time processing.”