戻る
「早戻しボタン」を押すと検索画面に戻ります。

今後説明を表示しない

[OK]

コーパス検索結果 (1語後でソート)

通し番号をクリックするとPubMedの該当ページを表示します
1            The networks were trained by fast-back-propagation.
2 l Neural Network (ANN) (Neuroshell 2) with a back propagation algorithm we have developed a prototype
3  at axon terminals, a process reminiscent of back-propagation algorithm for learning in neural networ
4 uration, and frequency, as well as dendritic back-propagation and synaptic plasticity.
5                                            A back-propagation aNN can be trained to predict hilar and
6                      The authors developed a back-propagation ANN with one hidden layer and eight pro
7                       We proposed to train a back-propagation artificial neural network (aNN) on a co
8                              A feed-forward, back-propagation artificial neural network (BP-ANN) was
9 ther method combines a standard feed-forward back-propagation artificial neural network (NN) with a l
10 citable dendrites with enhanced dendritic AP back-propagation, calcium electrogenesis, and induction
11 F) expressing dendrites revealed enhanced AP back-propagation compared to control neurones.
12 can be effectively compensated using digital back-propagation (DBP).
13  the activity dependence of action potential back-propagation in CA1 neurons.
14 e accuracies comparable to those obtained by back-propagation, in shorter time.
15 tion is achieved using multi-channel digital back-propagation (MC-DBP) and this technique is combined
16 er, the performance of multi-channel digital back-propagation (MC-DBP) for compensating fibre nonline
17  PME value of 29.91% at 118344 epochs by the back propagation network model.
18                                  An extended back-propagation network classified unfamiliar chemicals
19 mobility spectrum as input to a cascade-type back-propagation network.
20 res-support vector machines (LS-SVM) and PCA-back propagation neural network (PCA-BPNN) models with t
21 ighbor model and the modified version of the back propagation neural network) in CCM operate sequenti
22 is protocol is implemented for the case of a back-propagation neural network (BNN) and is used to dev
23  study we developed a new algorithm based on back-propagation neural network (BPNN) and MSD analysis
24 re built using support vector machine (SVM), back-propagation neural network (BPNN), convolutional ne
25                                          The back-propagation neural network algorithm is a commonly
26  piecewise linear discriminant analysis or a back-propagation neural network, an automated detection
27  +/- 2.75% while it is 82.28 +/- 6.45% using back-propagation neural networks.
28 ithm (SPA) and nonlinear techniques (BP-ANN, back propagation of artificial neural networks; LS-SVM,
29 t glutamatergic synapses is accompanied by a back propagation of depression to Input synapses on the
30 latter GEFs differentially enhanced front-to-back propagation of guidance cues through the monolayer
31 s regulate neuronal firing frequency and the back-propagation of action potentials (APs) into dendrit
32 pyramidal neuron dendrites by regulating the back-propagation of action potentials and by shaping syn
33  channels, which play a critical role in the back-propagation of action potentials and in the determi
34  the frequency of slow repetitive firing and back-propagation of action potentials in neurons and sha
35 action potential in the dendrites, limit the back-propagation of action potentials into the dendrites
36 ial steps in synaptic plasticity involve the back-propagation of action potentials into the dendritic
37                    These changes favored the back-propagation of action potentials into this dendriti
38 nal integration and attenuation of dendritic back-propagation of action potentials), we determined th
39 n that these channels shape EPSPs, limit the back-propagation of action potentials, and prevent dendr
40  CA1 hippocampal pyramidal neuron during the back-propagation of an action potential.
41            Feed-forward neural networks with back-propagation of error are trained to recognize the q
42 d that the channels serve to actively dampen back-propagation of somatic sodium spikes.
43 arises in the soma-axon hillock region, with back-propagation through excitable dendrites, whereas ot

WebLSDに未収録の専門用語(用法)は "新規対訳" から投稿できます。