Nicholas James Bailey's user avatar
Nicholas James Bailey's user avatar
Nicholas James Bailey's user avatar
Nicholas James Bailey
  • Member for 3 years, 10 months
  • Last seen more than a month ago
  • Cambridge, UK
2 votes

Is probabilities mean of predicted class (RandomForest) a consistent estimator of class recall?

2 votes

Should normalization be applied?

0 votes

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

2 votes

How to process the hyphenated english words for any nlp problem?

1 vote

How to increase model's prediction accuracy

4 votes

How can I label (predict) an unseen set of data based on an existing model?

7 votes
Accepted

Is autocorrelation of residuals a problem in machine learning?

1 vote

Holdout vs K-fold

2 votes
Accepted

Do I need to square a column if I want a neural network to try using that?

1 vote

How to keep only significant weights in an ANN

1 vote

Searching for a dataset that targets difficult words

0 votes

How would I classify this variable?

2 votes

I do feature engineering on the full dataset, is this wrong?

2 votes

Is there any way to explicitly measure the complexity of a Machine Learning Model in Python

0 votes

Is it a good practice to evaluate model performance by comparing the metrics of rescaled (inverse transformed) predictions and true target values?

1 vote

GRU and LSTM does not "take risk" predicting

0 votes

Calculating image text orientation in scanned documents

0 votes

Choosing an optimizer to perfectly fit a neural networks to training data

3 votes
Accepted

How to model user choice probability: binary model vs multi class model

2 votes

Interpreting a precision recall curve

0 votes
Accepted

What's the complexity of HDBSCAN?

1 vote
Accepted

Is it possible to compress a sequence of numbers through an autoencoder?

0 votes

Does Minibatch reduce drawback of SGD?

3 votes

Is it reasonable to train a neural network many times and cherry pick the best result based on test dataset accuracy?

1 vote

Deep learning theory: why are hidden layers necessary?

1 vote

Can points not being passed to the loss function influence it?

0 votes

How can one quickly look up people from a large database?

2 votes
Accepted

How to run Neural Net on GPU without python frameworks?

2 votes

Comparing soccer teams name

7 votes

Why are predictions from my LSTM Neural Network lagging behind true values?