98 Why do cost functions use the square error? 2016-02-10T21:52:30.730

41 Sparse_categorical_crossentropy vs categorical_crossentropy (keras, accuracy) 2018-12-01T06:28:06.650

35 Intuitive explanation of Noise Contrastive Estimation (NCE) loss? 2016-08-05T03:36:04.553

16 Parameterization regression of rotation angle 2017-11-21T15:33:00.287

15 Custom loss function with additional parameter in Keras 2017-11-22T22:24:28.950

13 Tensorflow Adjusting Cost Function for Imbalanced Data 2016-07-20T18:39:53.130

11 Interpreting the Root Mean Squared Error (RMSE)! 2018-08-14T22:28:37.953

10 What does from_logits=True do in SparseCategoricalcrossEntropy loss function? 2020-04-27T16:08:00.423

9 L2 loss vs. mean squared loss 2018-01-01T01:58:56.993

9 Validation showing huge fluctuations. What could be the cause? 2018-05-02T11:25:11.463

8 Keras categorical_crossentropy loss (and accuracy) 2017-06-22T20:04:18.330

8 What is the advantage of using log softmax instead of softmax 2018-11-04T18:29:28.263

7 Does keras categorical_cross_entropy loss take incorrect classification into account 2017-12-22T07:40:41.697

7 What is the difference between SGD classifier and the Logisitc regression? 2018-09-07T18:15:11.690

7 Validation loss is lower than the training loss 2018-10-14T13:16:02.000

7 Loss Function for Probability Regression 2019-02-09T00:14:07.110

7 What makes binary cross entropy a better choice for binary classification than other loss functions? 2019-06-07T15:41:11.670

6 Why is there a $2$ at the denominator of the mean squared error function? 2018-03-25T20:32:20.150

6 Classifier that optimizes performance on only a subset of the data? 2018-05-03T18:18:20.480

6 Why validation loss worsens while precision/recall continue to improve? 2018-05-30T13:52:33.950

6 What's the difference between Error, Risk and Loss? 2018-07-23T19:04:45.537

6 Keras - Implementation of custom loss function with multiple outputs 2019-11-19T17:42:52.047

5 Choice of objective function for log transformed data for feedforward NN 2016-05-13T14:22:56.333

5 Understanding autoencoder loss function 2016-12-06T22:43:19.713

5 Loss function to maximize sum of targets 2017-01-24T04:15:38.543

5 Cost-sensitive Logloss for XGBoost 2018-01-23T18:37:20.193

5 Train loss vs validation loss 2018-04-26T20:57:46.517

5 What algorithms will stuck in the local minimum? 2018-06-06T23:11:33.107

5 Loss function for optimising precision & recall / sensitivity & specificity? 2018-06-12T16:32:25.413

5 issue with early-stopping on f1 score with imbalanced data 2018-11-17T02:45:14.457

5 How to know which loss function is suitable for image classification? 2019-08-24T17:59:25.680

5 How to use "tree boosting" with a data-driven loss function 2020-10-02T18:25:51.057

4 which loss function (if any) optimizes the calibration graph 2016-08-01T14:44:46.700

4 Keras objective function shared between outputs 2017-02-23T03:00:57.410

4 Custom conditional loss function in Keras 2018-03-01T05:32:03.123

4 Can pinball loss be used to construct a prediction interval? 2018-06-17T17:49:50.183

4 Validation loss 2018-08-24T23:20:49.220

4 Why Gradient methods work in finding the parameters in Neural Networks? 2018-10-05T16:13:32.203

4 Why Huber loss has its form? 2019-01-25T09:33:15.360

4 How to recognise when to stop training based on Overfitting/Underfitting? 2019-03-26T21:31:44.923

4 How do I create a Keras custom loss function for a one-hot-encoded binary classifier? 2019-07-07T12:33:05.493

4 Loss function for multivariate regression where relationship between outputs matters 2019-12-19T01:58:31.567

4 Does convergence of loss function is always guarnteed? 2020-08-13T14:00:00.913

4 XGBoost custom objective for regression in R 2020-09-09T12:29:46.767

3 Which accuracy metric of a ML classifier can maximize map@K of a recommender system for an unbalanced dataset? 2015-09-02T11:40:08.637

3 does xgboost's eval_metric changes the loss function being optimized? 2016-03-27T05:50:49.920

3 Activation method and Loss function for multilabel multiclass classification 2016-09-12T13:01:16.533

3 XGBoost change loss function 2017-05-16T13:37:53.937

3 Keras custom loss - operation on additional data 2017-12-22T02:05:40.973

3 Loss function and data distribution for positive / negative examples 2018-02-10T12:12:10.447

3 Sementic segmentation data and model compile in Keras 2018-02-11T17:45:40.577

3 Understanding LSTM behaviour: Validation loss smaller than training loss throughout training for regression problem 2018-06-11T06:00:35.827

3 neural network function approximation with constraints 2018-06-26T06:49:40.123

3 Should I rescale losses before combining them for multitask learning? 2018-10-25T12:57:57.880

3 "help" decision tree by tying 2 features together 2018-10-31T08:31:04.947

3 Is empirical risk the same thing as loss function? 2019-01-16T14:41:34.693

3 How to utilize user feedback due to miss-classification when correct class label is unknown? 2019-03-05T10:21:03.393

3 MSE loss different in Keras and PyToch 2019-03-10T12:00:13.773

3 Is Adam's optimization susceptible to Local Minima? 2019-04-07T16:09:16.733

3 Having trouble figuring out how loss was calculated for SQuAD task in BERT paper 2019-04-20T01:57:53.193

3 Hinge Loss understanding and proof 2019-05-10T13:54:36.007

3 What is the relationship between "square loss" and "Mean squared error"? 2019-06-04T03:49:31.043

3 Is Categorical Crossentropy Loss always bounded in the [0, 1] interval? 2019-06-18T09:39:09.803

3 Tweedie Loss for Keras 2019-07-09T19:17:21.803

3 Pytorch doing a cross entropy loss when the predictions already have probabilities 2019-07-18T21:56:56.330

3 Poor performance of regression model for imbalanced data 2019-07-26T14:01:14.483

3 Heavy regression loss for false non 0 prediction 2019-08-23T14:58:41.413

3 Unable to transform (greatly performing) Autoencoder into Variational Autoencoder 2019-12-30T22:37:09.413

3 Interpreting Gradients and Partial Derivatives when training Neural Networks 2020-01-17T17:33:51.643

3 Loss being outputed as nan in keras RNN 2020-01-25T16:34:08.397

3 Does small batch size improve the model? 2020-04-24T17:12:57.370

3 VAE generates bad images. due to unbalanced loss functions? 2020-05-27T21:04:15.900

3 Making sense of loss and accuracy curves 2020-08-19T20:47:49.970

3 Why KL Divergence instead of Cross-entropy in VAE 2020-09-24T01:10:41.527

3 Train NN for balanced accuracy 2020-10-06T08:49:41.283

3 Which learning rate should I choose? 2020-11-13T08:14:40.293

3 no decrease loss and val_loss 2020-11-05T22:30:35.837

2 Why is each successive tree in GBM fit on the negative gradient of the loss function? 2016-02-21T05:41:22.113

2 Fractions or probabilities as training labels 2017-10-11T15:47:15.933

2 Fitting data with Fourier Series coefficients 2017-11-16T09:31:31.020

2 Losses of keras CNN model is not decreasing 2017-12-25T13:37:31.387

2 ROC-AUC loss for GRU Model: Cannot use tflearn's loss in keras 2018-02-15T01:38:58.983

2 Cost/loss functions for multi-tasking regression neural networks 2018-04-04T09:51:28.307

2 Class distribution discrepancy training/validation. Loss now uninterpretable? 2018-04-25T14:23:51.090

2 Keras/TensorFlow in R - Additional Vector to Custom Loss Function 2018-05-21T20:00:42.800

2 How to use a cross entropy loss function for each letter/digit in a captcha? 2018-05-29T17:04:55.833

2 Cross error loss function cause division by zero error 2018-06-01T16:15:01.197

2 How to create a custom loss function from sklearn metrics in Keras? 2018-06-09T17:21:45.897

2 Loss function range normalization 2018-07-09T09:58:47.700

2 How the combination of cross entropy loss and gradient descent penalizes and rewards 2018-07-10T22:52:36.327

2 Custom loss function which is included gradient in Keras 2018-07-16T10:39:28.380

2 Why are optimization algorithms slower at critical points? 2018-08-11T16:34:57.167

2 Tensorflow does not learn - same answer for various inputs 2018-08-18T11:33:22.223

2 Purpose of backpropagation in neural networks 2018-09-04T20:13:19.637

2 Constant validation loss & accuracy, training accuracy fluctuates 2018-09-10T12:27:55.920

2 Using SMAPE as a loss function for an LSTM 2018-11-12T11:38:56.847

2 Custom Loss Function on a Keras Neural Network 2018-11-20T19:56:38.233

2 What is non-decomposable and/or non-differentiable loss function? 2018-12-02T23:54:16.057

2 Geting batch size in keras custom loss 2019-02-20T10:07:10.453