A modified backpropagation algorithm with a linear output function is discussed from the viewpoint of its convenience in control tasks. Two methods are presented for teaching neural networks to act as an inverse plant...
详细信息
A modified backpropagation algorithm with a linear output function is discussed from the viewpoint of its convenience in control tasks. Two methods are presented for teaching neural networks to act as an inverse plant. In the simulation example a discrete integrator was used as the plant. The best results were obtained by a combination of both methods.< >
The problem of correctly evaluating noisy and incorrect data for the interpretation of ultrasonic sensor signals is an often encountered one. Neural networks, with their inherent characteristics of adaptivity and high...
详细信息
The problem of correctly evaluating noisy and incorrect data for the interpretation of ultrasonic sensor signals is an often encountered one. Neural networks, with their inherent characteristics of adaptivity and high fault- and noise-tolerance are well suited for such tasks. In this paper two neural network approaches are described for the control of the tracking behavior of an autonomous mobile robot. Input data are provided by a set of ultrasonic sensors mounted at the front of the vehicle. Two neural network learning strategies: backpropagation and reinforcement learning, are examined in a simulation and compared with respect to learning speed, capacity of tracking and the effort required to adapt the control networks of the real vehicle.< >
The authors examine the usefulness of the feedforward neural network as a controller. In particular, the authors consider as an example the problem of design of a power system stabilizer that has the structure of a cl...
详细信息
The authors examine the usefulness of the feedforward neural network as a controller. In particular, the authors consider as an example the problem of design of a power system stabilizer that has the structure of a classical feedforward artificial neural network. In this case, the controller is developed for a class of problems associated with linear plants. Certain observations are made regarding the generic behavior of systems with this type of controller structure. The authors incorporate a robustness criterion into the design as well as a conventional dynamic performance criterion.< >
The author provides calculus-of-variations techniques for the construction of backpropagation-through-time (BTT) algorithms for arbitrary time-dependent recurrent neural networks with both continuous and discrete dyna...
详细信息
The author provides calculus-of-variations techniques for the construction of backpropagation-through-time (BTT) algorithms for arbitrary time-dependent recurrent neural networks with both continuous and discrete dynamics. The backpropagated error signals are essentially Lagrange multipliers. The techniques are easy to handle because they can be embedded into the Hamiltonian formalism widely used in optimal control theory. Three examples of important extensions to the standard BTT-algorithm provide proof of the power of the method. An implementation of the BTT-algorithms which overcomes the storage drawbacks is suggested.< >
The authors used the Liapunov approach to derive a new set of sufficient conditions that explain the stability of feedforward networks. A simplification of these conditions results in a new recurrent backpropagation a...
详细信息
The authors used the Liapunov approach to derive a new set of sufficient conditions that explain the stability of feedforward networks. A simplification of these conditions results in a new recurrent backpropagation algorithm. This algorithm preserves the local updating characteristic of the original algorithm but is, at the same time, found to be quite effective even for problems which offered resistance to solution by L. B. Almeida's (1987) approach.< >
An optimal pruning algorithm for neural tree networks (NTN) is presented. The NTN is grown by a constructive learning algorithm that decreases the classification error on the training data recursively. The optimal pru...
详细信息
An optimal pruning algorithm for neural tree networks (NTN) is presented. The NTN is grown by a constructive learning algorithm that decreases the classification error on the training data recursively. The optimal pruning algorithm is then used to improve generalization. The pruning algorithm is shown to be computationally inexpensive. Simulation results on a speaker-independent vowel recognition task are presented to show the improved generalization using the pruning algorithm.< >
The authors propose a new methodology for controlling multitap capacitors in a power system using a three layer feedforward neural network. The neural network, in the proposed scheme is separately trained with two alg...
详细信息
The authors propose a new methodology for controlling multitap capacitors in a power system using a three layer feedforward neural network. The neural network, in the proposed scheme is separately trained with two algorithms namely backpropagation and a combined backpropagation-Cauchy's learning algorithm. Studies on 30 bus IEEE test system are carried out and quite satisfactory results are obtained. The inputs to the net are the real power, reactive power and voltage magnitude at a few selected buses and the network's outputs are the values of capacitive Var injection. Performance comparison is made between two algorithms and the combined backpropagation-Cauchy's algorithm is found to be better than the other.< >
A CMOS integrated circuit is described which is capable of implementing very large digital neural networks of the multilayer perceptron (MLP) form. It incorporates on-chip training using the backpropagation algorithm,...
详细信息
A CMOS integrated circuit is described which is capable of implementing very large digital neural networks of the multilayer perceptron (MLP) form. It incorporates on-chip training using the backpropagation algorithm, and the use of pseudorandom noise allows training with coarsely quantized weight values. Dynamic range and precision of the connection weights are automatically adjusted during training, thus allowing the circuit to adapt to different network sizes and topologies. The addition of a small, pseudorandom noise element allows the weights memory to be used more efficiently for large networks. Extensive simulation using a hardware description model over a range of problems has given a high degree of confidence in the design.< >
A novel adaptive channel equalizer based on the backpropagation algorithm applied to an associative network is presented. simulations are made for linear and nonlinear channels,. The performance is shown to be much be...
详细信息
A novel adaptive channel equalizer based on the backpropagation algorithm applied to an associative network is presented. simulations are made for linear and nonlinear channels,. The performance is shown to be much better than that obtained using the least-mean-square (LMS) algorithm for the nonlinear channel.
A data-compression algorithm for digital Holter recording using artificial neural networks (ANNs) is described. A three-layer ANN that has a hidden layer with a few units is used to extract features of the ECG (electr...
详细信息
A data-compression algorithm for digital Holter recording using artificial neural networks (ANNs) is described. A three-layer ANN that has a hidden layer with a few units is used to extract features of the ECG (electrocardiogram) waveform as a function of the activation levels of the hidden layer units. The number of output and input units is the same. The backpropagation algorithm is used for learning. The network is tuned with supervised signals that are the same as the input signals. One network (network 1) is used for data compression and another (network 2) is used for learning with current signals. Once the network is tuned, the common waveform features are encoded by the interconnecting weights of the network. The activation levels of the hidden units then express the respective features of the waveforms for each consecutive heartbeat.< >
暂无评论