On the "Identification and control of dynamical systems using neural networks"

By E. Rios-Patron, Richard D. Braatz. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

Citations in the corpus

Learning Continuous Control Policies by Stochastic Value Gradients (2015, methodology): “The idea of using a model to optimize a parametric policy around real trajectories is presented heuristically in [17] and [1] for deterministic policies and models.”
Deep learning in neural networks: An overview (2014, methodology): “1 RL Through NN World Models Yields RNNs With Deep CAPs In the special case of an RL NN controller C interacting with a deterministic environment, a separate FNN called M can learn to become C’s world model through system identification, predicting C’s inputs from previous actions and inputs (e.g., ”
Deep Drone Racing: Learning Agile Flight in Dynamic Environments (2018, background): “Indeed, the network has to learn the basic notion of stability from scratch in order to control an unstable platform such as a quadrotor [23].”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “The first combination of an RL RNN C and an UL RNN M was ours and dates back to 1990 [223, 222, 226, 227], generalizing earlier similar controller/model systems (CM systems) based on FNNs [298, 179]; compare related work [177, 119, 301, 300, 209, 120, 178, 302, 73, 45, 144, 166, 153, 196, 60][245, S”
New results on recurrent network training: unifying the algorithms and accelerating convergence (2000, background): “…or finite impulse response (FIR) networks [39]–[41], etworks with trainable delays [42], networks [43], memory neuron networks [44], generalized recursive neuron networks [45], [46], etc, have shown much success, and can be trained with some modifications of existing recurrent network algorithms.”
Composite Adaptive Fuzzy Output Feedback Control Design for Uncertain Nonlinear Strict-Feedback Systems With Input Saturation (2015, background): “INTRODUCTION IN THE PAST decades, for solving the tracking or regulation problems of nonlinear uncertain systems not satisfying the matching conditions, adaptive backstepping control has received much attention by using fuzzy logic systems (FLSs) [1]–[2] or neural networks (NNs) [3], and many signif”
Fuzzy Approximation-Based Adaptive Backstepping Optimal Control for a Class of Nonlinear Discrete-Time Systems With Dead-Zone (2016, background): “Recently, much interest has been received in the area of the fuzzy and neural model-based control [4]–[6] due to the excellent approximation ability of the fuzzy logic systems (FLSs) and the neural networks (NNs).”
Cautious Model Predictive Control Using Gaussian Process Regression (2017, unknown): “In this context, learning methods for automatically identifying dynamical models from data have gained significant attention in the past years [1], [2] and more recently for robotic applications [3], [4].”
Knowledge-Defined Networking (2016, background): “Conceptually, the KDN architecture borrows many ideas from other areas, notably from black-box optimization [5], neural-network in feedback control systems [6] and autonomic self-* architectures [7].”
Nonlinear System Identification: A User-Oriented Road Map (2019, background): “Calculating the derivative of the output of a NIIR system with respect to the model parameters boils down to computing the output of another nonlinear model [119].”
System identification of nonlinear state-space models (2011, background): “A key aspect of this activity is that it generally focuses on specific system classes such as those described by Volterra kernels [4], neural networks [37], nonlinear ARMAX (NARMAX) [29], and Hammerstein– Wiener [41] structures, to name just some examples.”
A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithms (2002, methodology): “of the system, and feed all the related states to the input as in [1].”
A hybrid of genetic algorithm and particle swarm optimization for recurrent network design (2004, methodology): “Example 2 (MISO Control): The controlled plant is the same as that used in [ 58 ], [27] and is given by”
Long-term time series prediction with the NARX network: An empirical evaluation (2008, methodology): “The resulting connectionist architecture is then called a NARX network [10,32], a powerful class of dynamical models which has been shown to be computationally equivalent to Turing machines [38].”
Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction (2006, background): “Narendra and Parthasarathy [16] have suggested two special forms of the nonlinear system model given in Eqs.”