Ieee transactions on neural networks文章索引

Parallel algorithms for finding a near-maximum independent set of a circle graph [0.03%] 圆图近最大独立集的并行算法研究

Y Takefuji,L L Chen,K C Lee et al. Y Takefuji et al.

A parallel algorithm for finding a near-maximum independent set in a circle graph is presented. An independent set in a graph is a set of vertices, no two of which are adjacent. A maximum independent set is an independent set whose cardinal...

IEEE transactions on neural networks. 1990;1(3):263-7. DOI:10.1109/72.80251 1990

The design of a neural network with a biologically motivated architecture [0.03%] 一种受生物体启发的神经网络的设计

R Braham,J O Hamblen R Braham

An associative neural network whose architecture is greatly influenced by biological data is described. The proposed neural network is significantly different in architecture and connectivity from previous models. Its emphasis is on high pa...

IEEE transactions on neural networks. 1990;1(3):251-62. DOI:10.1109/72.80250 1990

Standardization of neural network terminology [0.03%] 神经网络术语标准化

R C Eberhart R C Eberhart

Outlined are the initial activities of an ad hoc standards committee established by the IEEE Neural Networks Council to pursue this effort. A proposed list of frequently used terms to be considered by the committee is presented. Several pro...

IEEE transactions on neural networks. 1990;1(2):244-5. DOI:10.1109/72.80238 1990

Neural networks for control systems [0.03%] 神经网络在控制系统中的应用

P J Antsaklis P J Antsaklis

A description is given of 11 papers from the April 1990 special issue on neural networks in control systems of IEEE Control Systems Magazine. The emphasis was on presenting as varied and current a picture as possible of the use of neural ne...

IEEE transactions on neural networks. 1990;1(2):242-4. DOI:10.1109/72.80237 1990

A simple procedure for pruning back-propagation trained neural networks [0.03%] 一种用于剪枝误差反向传播训练的神经网络的简便方法

E D Karnin E D Karnin

The sensitivity of the global error (cost) function to the inclusion/exclusion of each synapse in the artificial neural network is estimated. Introduced are shadow arrays which keep track of the incremental changes to the synaptic weights d...

IEEE transactions on neural networks. 1990;1(2):239-42. DOI:10.1109/72.80236 1990

Learning of stable states in stochastic asymmetric networks [0.03%] 随机非对称网络中稳定态的学习

R B Allen,J Alspector R B Allen

Boltzmann-based models with asymmetric connections are investigated. Although they are initially unstable, these networks spontaneously self-stabilize as a result of learning. Moreover, pairs of weights symmetrize during learning; however, ...

IEEE transactions on neural networks. 1990;1(2):233-8. DOI:10.1109/72.80235 1990

Derivation of a class of training algorithms [0.03%] 一类训练算法的推导公式

S P Luttrell S P Luttrell

A novel derivation is presented of T. Kohonen's topographic mapping training algorithm (Self-Organization and Associative Memory, 1984), based upon an extension of the Linde-Buzo-Gray (LBG) algorithm for vector quantizer design. Thus a vect...

IEEE transactions on neural networks. 1990;1(2):229-32. DOI:10.1109/72.80234 1990

A novel objective function for improved phoneme recognition using time-delay neural networks [0.03%] 一种新的目标函数：使用时间延迟神经网络改进音素识别

J B Hampshire,A H Waibel J B Hampshire

Single-speaker and multispeaker recognition results are presented for the voice-stop consonants /b,d,g/ using time-delay neural networks (TDNNs) with a number of enhancements, including a new objective function for training these networks. ...

IEEE transactions on neural networks. 1990;1(2):216-28. DOI:10.1109/72.80233 1990

A theoretical investigation into the performance of the Hopfield model [0.03%] 霍普菲尔德模型性能研究的理论探讨

S B Aiyer,M Niranjan,F Fallside S B Aiyer

An analysis is made of the behavior of the Hopfield model as a content-addressable memory (CAM) and as a method of solving the traveling salesman problem (TSP). The analysis is based on the geometry of the subspace set up by the degenerate ...

IEEE transactions on neural networks. 1990;1(2):204-15. DOI:10.1109/72.80232 1990

Graph partitioning using annealed neural networks [0.03%] 用模拟退火神经网络进行图的分割

D E Van den Bout,T K Miller D E Van den Bout

A new algorithm, mean field annealing (MFA), is applied to the graph-partitioning problem. The MFA algorithm combines characteristics of the simulated-annealing algorithm and the Hopfield neural network. MFA exhibits the rapid convergence o...

IEEE transactions on neural networks. 1990;1(2):192-203. DOI:10.1109/72.80231 1990