Kari's user avatar
Kari's user avatar
Kari's user avatar
Kari
  • Member for 6 years, 2 months
  • Last seen more than a month ago
  • UK
14 votes
Accepted

Q-Learning: Target Network vs Double DQN

9 votes

Why do we need 2 matrices for word2vec or GloVe

8 votes
Accepted

How does Implicit Quantile-Regression Network (IQN) differ from QR-DQN?

6 votes
Accepted

Q learning - how to use experience replay, when playing against other agent?

4 votes

Why is my test data accuracy higher than my training data?

3 votes
Accepted

Nesterov Accelerated gradient is in correct order?

3 votes

How backpropagation through gradient descent represents the error after each forward pass

2 votes
Accepted

My LSTM can't reduce error down to zero, when overfitting

2 votes
Accepted

Synthetic Gradients - what's the practical benefit?

2 votes

How to determine if problem is solvable by neural network?

2 votes
Accepted

Neural Turing Machine - how the shifting works?

2 votes
Accepted

How much neural network theory required to design one?

2 votes
Accepted

RNNs for time series prediction - what configurations would make sense

2 votes

Hindsight Experience Replay, how to define a partially-known End-Goal

1 vote

LSTM training/prediction with no starting sequence

1 vote

Variable time units LSTM

1 vote

More layers in NN give worse result

1 vote
Accepted

Prioritized Experience Replay - why to approximate the Density Function?

1 vote
Accepted

LSTM: Taking previous output values as feature

1 vote
Accepted

use hidden layer of word2vec instead of 'one-hot', to reduce number of weights in other nets?

1 vote

Synthetic Gradients good number of Layers & neurons

1 vote
Accepted

recurrent weights on LSTM Data-gate? (the one with tanh)

1 vote
Accepted

Dueling Network gradient with respect to Advantage stream

1 vote

Neural Network backprop formula - Matrix dimensions won't match?

1 vote

Deep Q-Learning for physical quantity: q-values distribution not as expected

1 vote

Getting Validation Accuracy of 99% with MNIST with less than 10000 parameters CNN

0 votes
Accepted

Gradient Checking: MeanSquareError. Why huge epsilon improves discrepancy?

0 votes

Standarizing the Label to postive intergers in Machine Learning Classification task, why is it recommended?

0 votes

Muti-hot encoding vs Label-Encoding

0 votes
Accepted

Gradient Checking LSTM - how to get change in Cost across timesteps?