The reason for this apparent performance discrepancy between categorical & binary cross entropy is what user xtof54 has already reported in his answer below, i.e.: the accuracy computed with the Keras method evaluate is just plain wrong when using binary_crossentropy with more than 2 labels I would like to elaborate more on this, demonstrate the … Read more
I think that biases are almost always helpful. In effect, a bias value allows you to shift the activation function to the left or right, which may be critical for successful learning. It might help to look at a simple example. Consider this 1-input, 1-output network that has no bias: The output of the network … Read more
The output is the result of automatic evaluation via cross-validation. Of course it is not a prediction, because it has not been applied to new data yet. But you were not asked to execute a prediction anyway.
I decided to just implement a float head with an L1Loss in Pytorch and I created a simple but effective synthetic data set to test the implementation. The data set created images into which a number of small squares were randomly drawn. The training label was simply the number of squares divided by 10, a … Read more
If I’m not mistaken, you have two inputs X1, X2, and one target output. For each input consisting, of two numbers X1, X2, the appropriate output (“target”) is given. As a first step, you could sketch the seven data points – just draw the 3 ones and 4 zeroes at the right places on on … Read more
Outputs of a neural network are not probabilities (generally), so that could be a reason that you’re not getting the “1 – P” result you’re looking for. Now, if it’s simple logistic regression, you’d get probabilities as output, but I’m assuming what you said is true and you’re using a super-simple neural network. Also, what … Read more
Normally, if you are using a neural network, you should not have too different results between different runs on the same training set. So, first of all, check that your algorithm is working correctly using some standard benchmark problems (like iris/wisconsin from UCI repository) Regarding when to stop the training, there are two options: 1. … Read more
Save your model or the weights of your model: model.save(filename) np.save(filename, model.get_weights()) For loading, in the first case: from keras.models import load_model model = load_model(filename) In the second case: #recreate the model then: model.set_weights(np.load(filename)) Then: results = model.predict(batch_of_data)
You can use any IDE you want… you just need good algorithms, the IDE or language used does not really make much of a difference.
It is impossible. The lottery numbers are random – actually to be more specific, the system is chaotic. You would require the initial configuration (positions etc) to insane (possibly infinite) precision to be able to make any predictions. Basically, don’t even try it.