Mr Tsjolder from codidact's user avatar
Mr Tsjolder from codidact's user avatar
Mr Tsjolder from codidact's user avatar
Mr Tsjolder from codidact
  • Member for 8 years, 5 months
  • Last seen more than a week ago
49 votes

Which activation function for output layer?

11 votes

What is the jacobian for a neural network

10 votes
Accepted

What are the support vectors in a support vector machine?

6 votes

How to verify that an implementation of a neural network works correctly?

6 votes

Is using both training and test sets for hyperparameter tuning overfitting?

5 votes

How to calculate the variance of a partition of variables

5 votes
Accepted

VAE: what activation function (if any) to use for the last layer of my decoder if I don't want to assume any knowledge about the scale of my inputs?

4 votes

How much data do you need for a convolutional neural network?

4 votes

Supervised learning, unsupervised learning and reinforcement learning: Workflow basics

4 votes

Sum or mean of across gradients in weight-sharing convolutional networks (and why)?

3 votes

Adaptive Parzen Estimator

3 votes

Practical usefulness of PCA

2 votes
Accepted

Neural network, what is the error value for a layer?

2 votes

For neural networks, is mini-batching done purely because of memory constraints?

2 votes
Accepted

Deep Learning - why are we doing the forward pass on the whole dataset when using SGD

2 votes

Danger of setting all initial weights to zero in Backpropagation

2 votes

Difference between feedback RNN and LSTM/GRU

2 votes

Deriving Bellman's Equation in Reinforcement Learning

1 vote

can we perform sub-gradient updates in mini-batches

1 vote

LSTM, regression or classification output layer

1 vote

what is the correct formula of momentum for gradient descent?

1 vote

What is the difference between Multitask and Multiclass learning

1 vote
Accepted

Understanding number of rnn units in RNN networks

1 vote
Accepted

Why convolution output size is different using Toeplitz matrix?

1 vote

Is bias nothing but perceptron threshold value?

1 vote
Accepted

In backpropagation, why is weights_delta calculated as matrix multiplication of the outputs and delta? (and not of inputs and delta)

1 vote

Viewing a neural net loss function as a Gaussian Process

1 vote

With an LSTM, with training samples on 0->250, should it be able to extrapolate to unseen data(e.g. 250->500)?

1 vote

How we can compare loss and metrics evaluated on different sizes of training and validation sets?

0 votes

How can fully convolution neural networks handle images of different sizes?