Oscar's user avatar
Oscar's user avatar
Oscar's user avatar
Oscar
  • Member for 4 years, 9 months
  • Last seen more than a week ago
3 votes
Accepted

Removing seasonality in time series forecasting

2 votes
Accepted

Using Linear Regression to Learn Polynomial Regression

2 votes

What changes is the Neural Network back-propagation algorithm doing on the weights?

2 votes

How to do feature selection or feature engineering in datasets with a lot of features?

2 votes
Accepted

Get the confidence interval for prediction results with LSTM

1 vote

What is training data for Python tslearn KNeighborsTimeSeries?

1 vote

validation_split in time series data for lstm model

1 vote

Why does using tanh worsen accuracy so much?

1 vote

Ways to detect negation in Natural Language Processing?

1 vote
Accepted

Dealing with inputs of different sizes in time series forecasting

1 vote

How to implement my own loss function for Prototype learning using Keras Model

1 vote
Accepted

Mututal Information in sklearn

1 vote
Accepted

RNN/LSTM timeseries, with fixed attributes per run

1 vote

Which dataset for multivariate time series forecasting

1 vote

Training on multiple timeseries at different locations

1 vote
Accepted

How to compute the mean of weights of multiple models?

1 vote
Accepted

TypeError: object of type 'NoneType' has no len() when implementing neural network

0 votes
Accepted

CNN Deep Learning model fit problem with Tensorflow

0 votes
Accepted

Why we use an activation function for introducing nonlinearity instead of a polynomial Perceptron implementation?

0 votes

Problem with mord library function 'Logistic AT'

0 votes
Accepted

Dimension of output in Dense layer Keras

0 votes
Accepted

BPR TripletLoss Recommender System

0 votes

How to consider the effect of exclamation marks in sentiment analysis

0 votes

How to handle this kind of timeseries

0 votes

How to justify logarithmically scaled frequency for tf in tf-idf?

0 votes

Training a model with a series of text responses as input

0 votes

Why does neural network need loss as scalar?