Charlie Parker's user avatar
Charlie Parker's user avatar
Charlie Parker's user avatar
Charlie Parker
  • Member for 10 years, 6 months
  • Last seen more than a week ago
26 votes

How does one interpret histograms given by TensorFlow in TensorBoard?

7 votes

What does the term "Estimation error" mean?

5 votes

Curse of dimensionality: kNN classifier

4 votes

How to generate uniformly distributed points on the surface of the 3-d unit sphere?

4 votes

Does a Neural Network actually need an activation function or is that just for Back Propagation?

4 votes

What does the logit value actually mean?

4 votes

Why do we need sparsity for auto-encoders?

3 votes

Textbook on reinforcement learning

2 votes

How does one do sparse non-negative least squares using $K$ regularizers of the form $x^\top R_k x$?

2 votes

How to perform non-negative ridge regression?

2 votes

Where should I place dropout layers in a neural network?

2 votes

What is the proper way to report confidence intervals (or std, variance) for machine learning - especially wrt the loss and the accuracy?

1 vote
Accepted

What does the batch norm layer for MAML (model-agnostic meta-learning) do for during inference?

1 vote

Definition of normalized Euclidean distance

1 vote

How do coordinate wise meta-learning optimizers update learner networks?

1 vote

How does the realizability assumption imply that there is always a hypothesis that gets zero train error?

1 vote

Probabilistic interpretation of regression for justifying squared loss function

1 vote
Accepted

What is the predictive distribution of Bayesian supervised Learning? (rigorous argument)

1 vote

Why is the regularization penality equal to $\langle c , Kc \rangle_{R^n}$ when using the kernel trick in Tikhonov regularization?

1 vote

Probabilistic interpretation of regression for justifying squared loss function

0 votes

Why normalise the standard deviation of neural network input?

0 votes

What is the precise optimizer model from the paper Optimization as a model for few-shot learning?

0 votes

When does a logistic regression model have a unique solution?

0 votes

Can one formulate a optimization problem to choose a good step size for gradient descent?

0 votes

Can the Operating Characteristic for the LRT be derived from minimizing Bayes Risk $ \varphi(f) = \alpha P_F - \beta P_D + \gamma$?

0 votes

What does the term episode mean in meta-learning?

0 votes

accuracy of a regression prediction model

0 votes

Confidence interval given the population mean and standard deviation

0 votes

Why, in simple terms, is Cohen's D not affected by sample size but a T-Test is?

-1 votes

Significance test for large sample sizes