Top "Neural-network" questions

Network structure inspired by simplified models of biological neurons (brain cells).

How do I check if keras is using gpu version of tensorflow?

When I run a keras script, I get the following output: Using TensorFlow backend. 2017-06-14 17:40:44.621761: W tensorflow/core/platform/…

python tensorflow neural-network keras
Ordering of batch normalization and dropout?

The original question was in regard to TensorFlow implementations specifically. However, the answers are for implementations in general. This general …

python neural-network tensorflow conv-neural-network
Why must a nonlinear activation function be used in a backpropagation neural network?

I've been reading some things on neural networks and I understand the general principle of a single layer neural network. …

math machine-learning neural-network deep-learning
Loading a trained Keras model and continue training

I was wondering if it was possible to save a partly trained Keras model and continue the training after loading …

python tensorflow neural-network keras resuming-training
When should I use genetic algorithms as opposed to neural networks?

Is there a rule of thumb (or set of examples) to determine when to use genetic algorithms as opposed to …

artificial-intelligence machine-learning neural-network genetic-algorithm
Tensorflow One Hot Encoder?

Does tensorflow have something similar to scikit learn's one hot encoder for processing categorical data? Would using a placeholder of …

python machine-learning neural-network tensorflow
How to add regularizations in TensorFlow?

I found in many available neural network code implemented using TensorFlow that regularization terms are often implemented by manually adding …

python neural-network tensorflow deep-learning
TensorFlow - regularization with L2 loss, how to apply to all weights, not just last one?

I am playing with a ANN which is part of Udacity DeepLearning course. I have an assignment which involves introducing …

machine-learning neural-network tensorflow deep-learning regularized
Why do we need to call zero_grad() in PyTorch?

The method zero_grad() needs to be called during training. But the documentation is not very helpful | zero_grad(self) | …

python neural-network deep-learning pytorch gradient-descent
How to calculate the number of parameters of convolutional neural networks?

I can't give the correct number of parameters of AlexNet or VGG Net. For example, to calculate the number of …

machine-learning neural-network computer-vision vgg-net