Skip to main content
Ben's user avatar
Ben's user avatar
Ben's user avatar
Ben
  • Member for 7 years
  • Last seen this week
12 votes
Accepted

Dropout vs weight decay

10 votes

Image resizing and padding for CNN

10 votes

When is precision more important over recall?

7 votes
Accepted

Data preprocessing: Should we normalise images pixel-wise?

6 votes

Can one build linear models on "chunks" of the data set, if one can't build them on the entire data set?

5 votes

Confusion matrix - determine the values of FP FN TP and TN

5 votes
Accepted

Why does momentum need learning rate?

4 votes

Best neural network architecture for object detection without location

4 votes

Accuracy is lower than f1-score for imbalanced data

4 votes
Accepted

Untrained Network Giving 80% Accuracy

4 votes
Accepted

Train/Test size and bias

4 votes
Accepted

Predictive power of a dataset

4 votes
Accepted

Batch Normalization For Federated Learning

4 votes
Accepted

significance test and sample size estimation for classifiers

4 votes

How to continuously train a model with a stream of new incoming data

4 votes
Accepted

Why is $Y=\beta_0 x^{\beta_1} e$ a linear model?

3 votes

Confusion matrix. "How close I am to the diagonal?". Is there such metric?

3 votes
Accepted

Best framework for recognizing a specific cartoon character's face?

3 votes
Accepted

Is always converting a input vector into matrix and apply cnn's good idea?

3 votes

Is it possible to use NEAT networks for solving video games?

3 votes
Accepted

is there any way to plot ROC curves from weka

3 votes
Accepted

Interpretation of 'recall' as a conditional probability P( X=>+ | X=+ )

2 votes

Max-pooling vs. zero padding: Loosing spatial information

2 votes
Accepted

How do we decide which kernel needs to be used in SVM?

2 votes

Crop background from Image

2 votes
Accepted

Geometric and harmonic means in ensembling methods

2 votes
Accepted

Using handcrafted features in CNN

2 votes
Accepted

Space between an object and the ground truth bounding box

2 votes
Accepted

How is the "loss" calculated which is supplied by the callback log in Keras?

2 votes
Accepted

Why could an overfitted CNN model have a higher validation accuracy?