User Dan D.

17 votes

3 answers

13k views

What is the difference between Q-learning, Deep Q-learning and Deep Q-network?

asked Jan 22, 2021 at 9:41

12 votes

1 answer

3k views

What are all the different kinds of neural networks used for? [closed]

asked Sep 23, 2019 at 8:33

9 votes

1 answer

2k views

What is the formula for the momentum and Adam optimisers?

asked Jan 13, 2020 at 7:04

5 votes

3 answers

767 views

Why is symbolic AI not so popular as ANN but used by IBM's Deep Blue?

asked Jul 20, 2020 at 7:07

4 votes

1 answer

3k views

Is a reward given at every step or only given when the RL agent fails or succeeds?

asked Jul 21, 2020 at 9:59

4 votes

3 answers

4k views

In which cases is the categorical cross-entropy better than the mean squared error?

asked Jan 19, 2020 at 0:56

4 votes

1 answer

172 views

Is it possible to do K-nearest-neighbours before training DNN

asked Sep 26, 2019 at 2:04

3 votes

2 answers

763 views

How to use LSTM to generate a paragraph

asked Jan 2, 2020 at 3:11

2 votes

1 answer

134 views

When would bias regularisation and activation regularisation be necessary?

asked Jul 18, 2020 at 1:13

2 votes

1 answer

2k views

How to avoid being stuck local optima in q-learning and q-network

asked Mar 17, 2021 at 2:11

2 votes

1 answer

81 views

How to handle class imbalance when the actual data are that way

asked Apr 19, 2021 at 2:58

2 votes

1 answer

1k views

How to make DNN learn multiplication/division?

asked Dec 26, 2019 at 19:27

2 votes

0 answers

321 views

Is Gradient Descent algorithm a part of Calculus of Variations?

asked Feb 4, 2020 at 8:00

2 votes

1 answer

215 views

What is the mean in the variational auto-encoder?

asked Feb 4, 2020 at 9:17

2 votes

1 answer

405 views

GANs: Should Generator update weights when Discriminator says false continuously

asked Feb 28, 2020 at 23:23

1 vote

1 answer

232 views

Random value generator using a single neuron or DNN

asked May 11, 2020 at 4:30

1 vote

1 answer

125 views

What should the output of a neural network that needs to classify in an unsupervised fashion XOR data be?

asked Jul 22, 2020 at 5:57

1 vote

1 answer

492 views

Why is exp used in encoder of VAE instead of using the value of standard deviation alone?

asked Feb 6, 2020 at 6:53

1 vote

1 answer

104 views

What is the equation of the separation line for this neuron with identity activation?

asked Feb 26, 2020 at 2:08

1 vote

1 answer

1k views

YOLOv3 Model Structure: Why is filters = (classes + coords + 1) * num?

asked Feb 27, 2020 at 8:26

1 vote

2 answers

2k views

What are the reasons behind slow YOLO training?

asked Feb 28, 2020 at 4:03

1 vote

1 answer

2k views

Why is Standard Deviation based on L2 Variance and not L1 Variance

asked Feb 4, 2020 at 8:19

1 vote

1 answer

264 views

How to plot Loss Landscape with more than 2 weights in the network

asked Oct 18, 2019 at 3:28

1 vote

1 answer

125 views

How many layers and neurons on the layers does a neural network need for for sales prediction?

asked May 9, 2017 at 6:10

1 vote

2 answers

428 views

Why is embedding important in NLP, and how does autoencoder work?

asked Oct 1, 2019 at 2:59

1 vote

1 answer

115 views

TensorFlow estimator DNNClassifier fails to fit simple data

asked Aug 23, 2019 at 2:34

1 vote

1 answer

81 views

How could logistic loss be used as loss function for an ANN?

asked Jul 31, 2020 at 8:34

0 votes

1 answer

106 views

How to train a policy model incrementally to solve a problem similar to the vehicle routing problem?

asked Jan 21, 2021 at 2:42

0 votes

0 answers

133 views

Any RL approaches for this 2D space optimization problem?

asked Apr 14, 2021 at 7:21

0 votes

1 answer

426 views

What are the popular approaches to estimating the Q-function?

asked Feb 1, 2021 at 12:16

Stack Exchange Network

46 Questions

What is the difference between Q-learning, Deep Q-learning and Deep Q-network?

What are all the different kinds of neural networks used for? [closed]

What is the formula for the momentum and Adam optimisers?

Why is symbolic AI not so popular as ANN but used by IBM's Deep Blue?

Is a reward given at every step or only given when the RL agent fails or succeeds?

In which cases is the categorical cross-entropy better than the mean squared error?

Is it possible to do K-nearest-neighbours before training DNN

How to use LSTM to generate a paragraph

When would bias regularisation and activation regularisation be necessary?

How to avoid being stuck local optima in q-learning and q-network

How to handle class imbalance when the actual data are that way

How to make DNN learn multiplication/division?

Is Gradient Descent algorithm a part of Calculus of Variations?

What is the mean in the variational auto-encoder?

GANs: Should Generator update weights when Discriminator says false continuously

Random value generator using a single neuron or DNN

What should the output of a neural network that needs to classify in an unsupervised fashion XOR data be?

Why is exp used in encoder of VAE instead of using the value of standard deviation alone?

What is the equation of the separation line for this neuron with identity activation?

YOLOv3 Model Structure: Why is filters = (classes + coords + 1) * num?

What are the reasons behind slow YOLO training?

Why is Standard Deviation based on L2 Variance and not L1 Variance

How to plot Loss Landscape with more than 2 weights in the network

How many layers and neurons on the layers does a neural network need for for sales prediction?

Why is embedding important in NLP, and how does autoencoder work?

TensorFlow estimator DNNClassifier fails to fit simple data

How could logistic loss be used as loss function for an ANN?

How to train a policy model incrementally to solve a problem similar to the vehicle routing problem?

Any RL approaches for this 2D space optimization problem?

What are the popular approaches to estimating the Q-function?