Neural networks for optimization and signal processing

By Andrzej S. Cichocki, R. Unbehauen. 1993

How researchers see this paper

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

Citations in the corpus

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., ”
Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems (2018, background): “…in the context of identifying nonlinear dynamics, there exist several deterministic and probabilistic tools including radial basis functions [6], neural networks [7], Gaussian processes [8, 9, 10, 11, 12], and nonlinear auto-regressive models such as NARMAX [13] and recurrent neural networks [14].”
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”
Blind Source Separation and Independent Component Analysis: A Review (2005, background): “Generally speaking, in signal processing applications, the overdetermined (m > n) system of linear equations (2) describes filtering, enhancement, deconvolution and identification problems, while the underdetermined case describes inverse and extrapolation problems [51, 40].”
Trajectory-Tracking Control of Mobile Robot Systems Incorporating Neural-Dynamic Optimized Model Predictive Approach (2016, methodology): “, k, P (·) is the piecewise-linear activation function, from [37] and [38], it can be implemented using operational amplifiers.”
Pattern recognition and neural networks (1996, background): “[6], [12]) – After the completion of the training phase, the parameters of the network are frozen to their converged values and the network is now ready for classification.”
1D Convolutional Neural Networks and Applications: A Survey (2019, unknown): “[-1,1] Ch.”
Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability (2001, background): “(Cichocki and Unbehauen 1993; Zhang and Constantinides 1992), neural networks are becoming one of the most powerful and appealing nonlinear signal processors for a variety of signal processing applications.”
Super-resolution target identification from remotely sensed images using a Hopfield neural network (2001, methodology): “5 shows each synthetic image subsampled (using a 7 7 mean filter) to generate an 8 8 pixel image, which causes mixing of the two classes (white and black) at the shape boundaries, producing eight proportion images and imitating the effect of class mixing within remotely sensed imagery.”
Blind Source Separation and Independent Component Analysis : A Review (2004, background): “Generally speaking, in signal processing applications, the overdetermined (m > n) system of linear equations (2) describes filtering, enhancement, deconvolution and identification problems, while the underdetermined case describes inverse and extrapolation problems [51] [40].”
Meta learning evolutionary arti ! cial neural networks (2004, methodology): “The strong interest in neural networks in the scienti!c community is fueled by the many successful and promising applications especially to tasks of optimization [26], ∗ Tel.”
Optimization and pole assignment in control system design (2001, background): “Finally, there has been some interesting work recently in [27, 37], on applying gradient flow techniques [16] to the PAP.”
Wiley‐Interscience Series in Discrete Mathematics and Optimization (2011, unknown): “For applications of neural networks to optimization, signal processing, and control problems, see [19] and [48].”