neural-network

问题 I am new to Artificial neural network but please help me with this question? I am trying to implement an artificial neural network for character recognition (using MLP, and SNN), do I need to have same number of neurons in the output layer as the numbers of characters required to be identified. For example do I need to have 26+26+10 neurons in output layer if I want my network to be able to identify capital letters, small letters and digits. what if I had to identify all the characters in the

问题 I tried to run this code with my data but I obtained this error: "ValueError: shapes (3,126) and (3,126) not aligned: 126 (dim 1) != 3 (dim 0)" I'm doing the neural network and I don't want to use libraries which are suitable for Neural Network like TensorFlow. X = pd.read_excel(r"C:\\users\Hasan\Desktop\ANN\x.xlsx") y = pd.read_excel(r"C:\\users\Hasan\Desktop\ANN\y.xlsx") xPredicted = pd.read_excel(r"C:\\users\Hasan\Desktop\ANN\xpredict.xlsx") self.W1 = np.random.randn(self.inputSize, self

问题 I would like to try out an idea about autoencoder. The model is like this: input (pictures) - conv2d - pooling - dense - dense(supervised output) - dense - conv - upsampling - output (pictures) If it is possible to train the NN having desired outputs for dense(supervised output) and output (pictures) ? In other words, I want to make a classifier-and-back. 回答1: This can be done with the Keras functional API (https://keras.io/getting-started/functional-api-guide/). A minimal example, where the

问题 I am facing this error while running a pytorch script. Can anyone help me? Expected object of scalar type Long but got scalar type Int for argument #2 'target' 来源： https://stackoverflow.com/questions/54262455/expected-long-but-got-int-while-running-pytorch-script

问题 I used ffnew functions many times but when I am trying to create a simple feed forward network such that the input vector is P=[1;2;3;4] and the desired output is T=[1 ;0;0;1] . So i only have one sample input vector The code is net = newff(P,T,[4 1],{'tansig','tansig'}); net=train (net,P,T); When I write the last line I got: ??? Error using ==> plus Matrix dimensions must agree. Error in ==> calcperf2 at 163 N{i,ts} = N{i,ts} + Z{k}; Error in ==> trainlm at 253 [perf,El,trainV.Y,Ac,N,Zb,Zi

问题 I want to write a neural network which look for a x^2 distribution without a predefined model. Precisely, it is given some points in [-1,1] with their squares to train, and then it would have to reproduce and predict similar for e.g. [-10,10]. I've more or less done it - without datasets. But then I tried to modify it in order to use datasets and learn how to use it. Now, I succeded in making the program run, but the output is worse then before, mainly it's constant 0. Previous version was

问题 I am currently working on a classification problem with two classes in ScikitLearn with the solver adam and activation relu. To explore if my classifier suffers from high bias or high variance, I plotted the learning curve with Scikitlearns build-in function: https://scikit-learn.org/stable/auto_examples/model_selection/plot_learning_curve.html I am using a Group-K_Fold crossvalidation with 8 splits. However, I found that my learning curve is strongly dependent on the batch size of my

问题 I am encountering this error when trying to use the confusion matrix in my binary classification problem. Y and Yhat are both numpy arrays. I have tried the .argmax as the proposed solution - I don't get the error anymore but the output is not the confusion matrix that I know. Accuracy: 0.9982449999999999 Accuracy: 0.9983374013937532 shape of y = (1, 200000) shape of yhat = (1, 200000) The error ValueError Traceback (most recent call last) <ipython-input-13-ebb660b4585a> in <module>() 12

问题 Here is a short review of triplet learning. I'm using three convolutional neural networks with shared weights in order to generate faces embeddings ( anchor , positive , negative ), with the loss described here. Triplet loss: anchor_output = ... # shape [None, 128] positive_output = ... # shape [None, 128] negative_output = ... # shape [None, 128] d_pos = tf.reduce_sum(tf.square(anchor_output - positive_output), 1) d_neg = tf.reduce_sum(tf.square(anchor_output - negative_output), 1) loss = tf

问题 I try to make a custom loss function in Keras. I want to make this loss function The dimension of output is 80. Batch size is 5000. So I build this loss function below. But this doesn't work. def normalize_activation(y_true, y_pred): nb_divide = K.reshape(K.sqrt(K.sum(K.square(y_pred), axis=1)),(5000, 1)) nb_divide=numpy.tile(nb_divide,80) predicted=numpy.divide(y_pred,nb_divide) return K.sum(K.square(y_true-predicted)) ValueError: setting an array element with a sequence. This error occurs.