New posts in neural-network

scale the loss value according to "badness" in caffe

neural-network deep-learning caffe conv-neural-network

In which cases is the cross-entropy preferred over the mean squared error? [closed]

machine-learning neural-network backpropagation mean-square-error cross-entropy

Keras LSTM: predict multiple sequences from single input array

python numpy tensorflow keras neural-network

Can neural networks approximate any function given enough hidden neurons?

machine-learning neural-network

gensim word2vec: Find number of words in vocabulary

python neural-network nlp gensim word2vec

Why does prediction needs batch size in Keras?

neural-network classification keras

What is a projection layer in the context of neural networks?

machine-learning nlp neural-network word2vec

Why do we need to explicitly call zero_grad()? [duplicate]

neural-network deep-learning pytorch gradient-descent

Octave : logistic regression : difference between fmincg and fminunc

algorithm machine-learning neural-network octave

PyTorch / Gensim - How to load pre-trained word embeddings

python neural-network pytorch gensim embedding

DCGAN debugging. Getting just garbage

python neural-network pytorch generative-adversarial-network

Tensorflow: How to replace or modify gradient?

python tensorflow neural-network

Python scikit learn MLPClassifier "hidden_layer_sizes"

python python-2.7 scikit-learn neural-network

What is the number of filter in CNN?

machine-learning neural-network theano convolution

Meaning of an Epoch in Neural Networks Training

machine-learning artificial-intelligence neural-network pybrain

Does Caffe need data to be shuffled?

c++ machine-learning neural-network deep-learning caffe

How useful is Turing completeness? are neural nets turing complete?

neural-network finite-automata turing-complete state-machine

caffe data layer example step by step

neural-network deep-learning caffe pycaffe

How to log Keras loss output to a file

python logging machine-learning neural-network keras

How does one debug NaN values in TensorFlow?

python machine-learning neural-network tensorflow conv-neural-network