Stable Adaptive Neural Network Control

Ge, Shuzhi Sam; Hang, C.C.; Lee, T. H.; Zhang, Tao

doi:10.1007/978-1-4757-6577-9

Cited by 630 publications

(527 citation statements)

References 88 publications

(183 reference statements)

Supporting

Mentioning

525

Contrasting

Unclassified

Order By: Relevance

“…In the special case of an RL FNN controller C interacting with a deterministic, predictable 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., Werbos, 1981Werbos, , 1987Munro, 1987;Jordan, 1988;Werbos, 1989b,a;Robinson and Fallside, 1989;Jordan and Rumelhart, 1990;Schmidhuber, 1990d;Narendra and Parthasarathy, 1990;Werbos, 1992;Gomi and Kawato, 1993;Cochocki and Unbehauen, 1993;Levin and Narendra, 1995;Miller et al, 1995;Ljung, 1998;Prokhorov et al, 2001;Ge et al, 2010). Assume M has learned to produce accurate predictions.…”

Section: Rl Through Nn World Models Yields Rnns With Deep Capsmentioning

confidence: 99%

Deep learning in neural networks: An overview

2015

View full text Add to dashboard Cite

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.LATEX source: http://www.idsia.ch/˜juergen/DeepLearning8Oct2014.tex Complete BIBTEX file (888 kB): http://www.idsia.ch/˜juergen/deep.bib Preface This is the preprint of an invited Deep Learning (DL) overview. One of its goals is to assign credit to those who contributed to the present state of the art. I acknowledge the limitations of attempting to achieve this goal. The DL research community itself may be viewed as a continually evolving, deep network of scientists who have influenced each other in complex ways. Starting from recent DL results, I tried to trace back the origins of relevant ideas through the past half century and beyond, sometimes using "local search" to follow citations of citations backwards in time. Since not all DL publications properly acknowledge earlier relevant work, additional global search strategies were employed, aided by consulting numerous neural network experts. As a result, the present preprint mostly consists of references. Nevertheless, through an expert selection bias I may have missed important work. A related bias was surely introduced by my special familiarity with the work of my own DL research group in the past quarter-century. For these reasons, this work should be viewed as merely a snapshot of an ongoing credit assignment process. To help improve it, please do not hesitate to send corrections and suggestions to juergen@idsia.ch.

show abstract

Section: Rl Through Nn World Models Yields Rnns With Deep Capsmentioning

confidence: 99%

Deep learning in neural networks: An overview

2015

View full text Add to dashboard Cite

show abstract

“…Several function approximators can be applied for this purpose, such as, radial basis function (RBF) neural networks [13,14], high-order neural networks [15] and fuzzy systems [16], which can be described as W T S(z) with input vector z ∈ R n , weight vector W ∈ R l , node number l, and basis function vector S(z) ∈ R l . Universal approximation results indicate that, if l is chosen sufficiently large, then W T S(z) can approximate any continuous function to any desired accuracy over a compact set [15,14].…”

Section: Linearly Parameterized Neural Approximatormentioning

confidence: 99%

Approximation Based Adaptive Tracking Control of Uncertain Nonholonomic Mechanical Systems

Wang

Obeng

et al. 2009

Control and Intelligent Systems

View full text Add to dashboard Cite

Abstract-In this paper, the trajectory tracking control problem of uncertain nonholonomic mechanical systems is investigated. By separately considering kinematic and dynamic models of a nonholonomic mechanical system, a new adaptive tracking control is proposed based on neural network approximation. The proposed design consists of two steps. First, the nonholonomic kinematic subsystem is transformed into a chained form, and the corresponding optimal control is derived. Second, an adaptive neural control is designed for the dynamic subsystem to make the outputs of the dynamic subsystem asymptotically track the optimal control signals chosen for the kinematic subsystem. The proposed control is simulated on a unicycle wheeled mobile robot.

show abstract

“…They naturally arise from physics and can be found in various fields such as electrical and electronic engineering (generation of electric power, as well as electrical devices such as motors and transformers), aeronautical or automotive. See, for example, the works by Brockett and Wood, Corona, Giua and Seatzu, Feuer, Goodwin and Salgado, Ge, Hang, Lee and Zhang (see [1], [3], [5], [6]). Roughly speaking, a switched system is a family of continuous-time (or discrete-time) dynamical subsystems and a rule that determines the switching between them.…”

Section: Introductionmentioning

confidence: 99%