Questions tagged [loss]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
4 votes
0 answers
260 views

How Does the Reward Model in ChatGPT Calculate Losses?

Reading the InstructGPT paper(which seems to be what ChatGPT was built off of), I found this equation for the reward function. However, I'm struggling to understand how this equation is used to ...
itisyeetimetoday's user avatar
2 votes
3 answers
2k views

Custom loss function for regression

I am trying to write a custom loss function for a machine learning regression task. What I want to accomplish is following: Reward higher preds, higher targets Punish higher preds, lower targets ...
Filip's user avatar
  • 21
2 votes
1 answer
2k views

HuggingFace Transformers is giving loss: nan - accuracy: 0.0000e+00

I am a HuggingFace Newbie and I am fine-tuning a BERT model (distilbert-base-cased) using the Transformers library but the training loss is not going down, instead ...
JasonExcel's user avatar
2 votes
0 answers
293 views

How to calculate MAE and threshold in a multivariate time series

I'm trying to understand how to calculate the MAE in my time series and then the thresholds to understand which of my data in the test set are anomalies. I'm following this tutorial, which is based on ...
Fabio's user avatar
  • 53
1 vote
1 answer
85 views

What does that mean if the loss looks like this?

I have a problem. I have trained a model. And as you can see, there is a zigzag in the loss. In addition, the validation loss is increasing. What does this mean if you only look at the training curve? ...
Test's user avatar
  • 89
1 vote
1 answer
8k views

Should Discriminator Loss increase or decrease?

This question is purely based on the theoretical aspect of GANs. So, when training a GAN how should the discriminator loss look like? Should the loss of discriminator increase (as the generator is ...
Sai Sreenivas's user avatar
1 vote
3 answers
99 views

Regression problem with Deep Learning

I'm working on the Housing Price dataset, where the target is to predict the housing price. The price of the house will always be positive and according to me, it's possible that the model can predict ...
vipin bansal's user avatar
  • 1,262
1 vote
0 answers
13 views

I can't understand why the validation and training loss almost constant and not converging?

...
user731995's user avatar
1 vote
0 answers
100 views

Calculationg perplexity (in natural language processing) manually

I am trying to understand Perplexity within Natural Language Processing as a metric more fully. And I am doing so by creating manual examples to understand all the component parts. Is the following ...
Piskator's user avatar
  • 125
1 vote
1 answer
17 views

The proper loss function for regression that prediction values do not lie on one side of the real values

I'm doing a prediction task using machine learning. First I'm doing a regression task, then I use the values to predict its class. I used MSE as loss function. However, my prediction values are ...
user900476's user avatar
1 vote
0 answers
19 views

Should the model be defined again before training it to new data?

I wanted to fit the LSTM model on new data set in a loop so I have implemented it like this ...
Stupid_Intern's user avatar
1 vote
0 answers
23 views

The case of (1,478) dim and parameters of neural network to find out

colleagues, actually I am kind'a new to NN, but hard trying.. I have data: Index: 40073 entries (excluded from training, UID) Columns: 484 entries dtypes: bool(468), float64(2), int64(13), object(1) I ...
Gleb Karpushkin's user avatar
1 vote
0 answers
43 views

How to interpret high loss value from model.evaluate() on test data

I'm collecting some metrics for my model's performance using: ...
TomSelleck's user avatar
1 vote
1 answer
140 views

Accuracy graph of binary classification by CNN [closed]

Why in binary classification of images with CNN the loss and accuracy graph are so unstable? I mean accuracy of validation test does not increase smoothly, it goes to 80%, then comes to 60%, then ...
Nagh's user avatar
  • 129
0 votes
1 answer
642 views

Logarithmic scale for a learning curve [closed]

I'm plotting the learning curve with Python with the following code: ...
Bambeil's user avatar
  • 111
0 votes
1 answer
42 views

Is there a way I can double the punishment when model mis-classing to a specific class?

As the title I asked. For example: a model that predicts the probability of a stock price rising/falling. Let's say this is a triple-classification problem. If it predicts "RISING", while ...
EvilRoach's user avatar
  • 101
0 votes
2 answers
76 views

Val loss initially decreases, then increases

I've created an LSTM model to predict 1 output value from 8 features. My loss constantly decreases and my val loss also decreases from the start, however it begins to increase after so many epochs. ...
ahy's user avatar
  • 1
0 votes
1 answer
704 views

Keras loss object and shapes

I'm at a loss. I've been staring at this problem for a while and I'm unsure how to proceed. I've been constructing a script to train a model for object detection based on a dataset I've compiled. I've ...
Hiromi's user avatar
  • 1
0 votes
1 answer
153 views

Decreasing Learning Rate doesn't improve the results

In theory and what people are doing (e.g. Paper) decreasing the learning rate should help the optimizer to go "deeper into the valley" and thus decrease the loss and increase the metric. ...
wuiwuiwui's user avatar
  • 101
0 votes
1 answer
447 views

Training loss = 0, training accuracy =1, validation and test around 85%

I have created different CNNs for doing image classification. The dataset is this: https://www.kaggle.com/crowww/a-large-scale-fish-dataset There are 9 classes, and each class contains 1000 images of ...
CasellaJr's user avatar
  • 229
0 votes
1 answer
756 views

Is it vital to use weighted metrics with weighted loss functions?

When one has an imbalanced machine learning problem, let's say a binary classification problem where class 0 is a majority class and class 1 is a minority class. Here class 1 is the most important ...
PinkBanter's user avatar
0 votes
0 answers
13 views

Tensorflow keras training/validation loss digits of precision

I have my model defined with certain structure and now just permuting between filter counts and number of layers of structure. I am watching the output of model.fit() such as ...
user2624395's user avatar
0 votes
0 answers
25 views

Training rate of "convergence" vs viability of network architecure

I am still fairly new to modern neural networks (dabbled in the 90's when convolution was called neocognition which I didn't explore regrettably). I read the suggestions after typing in the above ...
user2624395's user avatar
0 votes
0 answers
9 views

What I do wrong with my speech recognition CTC model

I want to train an english speech to text model using architecture similar to deepspeech. In general it has 4 blocks: feature extraction I used melspectrogram. (I used n_mels=80) This translates (...
Захар Наумець's user avatar
0 votes
0 answers
47 views

Custom loss function for multi label classification in catboost?

I have a data frame which I want to use for multi class classification problem. There are total 6 classes (say a, b, c, d, e, f). I want to improve the precision for three classes (say a, b, c) i.e. ...
SUNITA GUPTA's user avatar
0 votes
0 answers
49 views

Train neural network to predict multiple distributions

I aim to train a neural network to predict 2 distributions (10 quantiles, i.e. deciles) at 5 time points. So my y is of shape: ...
A_Murphy's user avatar
0 votes
0 answers
92 views

Siamese Network in TensorFlow employing Triplet Loss

I am constructing a siamese network using tensorflow which uses triplet loss. My inputs are of shape (100,100,1) and I have made a CNN embed_model to so that the output is a tensor with 50 points. Now ...
Adveat Prasad Karnik's user avatar
0 votes
0 answers
25 views

flat validation loss (underfitting or goodfitting)

if we have a loss like this plot, is it kind of underfitting or goodfitting? Error results: Training Process:
stack offer's user avatar
0 votes
0 answers
37 views

Why is there a 0.5 in this loss?

I'm reading this paper and I don't understand why the squared L2-norm is also multiplied by 0.5 in the loss. They want a loss that measures the distance between two feature maps. Why don't they use ...
Alessandro Polidori's user avatar
0 votes
0 answers
118 views

training loss decreases but training accuracy is also decreasing with epochs

I am working on the classification problem where by I am having a hinge loss function + other loss terms to optimize for which the input is the output from tanh layer at the end. But I can't reveal ...
POOJA GUPTA's user avatar
0 votes
1 answer
170 views

why the accuracy result and the loss result of an ANN model is inconsistent?

I trained a model based on an ANN and the accuracy is 94.65% almost every time while the loss result is 12.06%. Now my question is shouldn't the loss of the model be (100-94 = 6%) or near it? Why it ...
kazi fahim lateef's user avatar
0 votes
0 answers
238 views

Is my CNN model overfitting or underfitting?

I would like to be sure of whether the model is overfitting or undercutting. Being new to this, is there any specific point to identify when to stop the training process. Any help in this regard would ...
Anna's user avatar
  • 1
0 votes
0 answers
88 views

Q values loss per episode and mean absolute error

I am new to deep reinforcement learning! I am following this code for my adaptation problem (doing actions) https://github.com/jaromiru/AI-blog/blob/master/CartPole-DQN.py I am wondering how I can ...
imen kanzali's user avatar
0 votes
0 answers
63 views

How to increase accuracy and decrease loss of my model

https://jovian.ai/casella0798/badmodel I created the model above to predict red wine quality. I have 6 classes, from 3 to 8. Dataset is unbalanced, with a lot of classes 5 and 6. My model performs ...
CasellaJr's user avatar
  • 229
0 votes
1 answer
250 views

Interpreting Categorical Crossentropy Loss

I would like to ask for clarification about the loss values outputted during training using Categorical Crossentropy as the loss function. If I have 11 categories, and my loss is (for the sake of the ...
Michael Pulis's user avatar
-1 votes
1 answer
76 views

Why are the Loss and Accuracy metrics not suitable?

I have read in a book where it was described that Loss and Accuracy are only conditionally suitable for a statement strength. Other metrics are used like Precision, Recall, ... . Does anyone know a ...
Ella's user avatar
  • 179
-2 votes
1 answer
87 views

Why do people prefer $(target-actual)^2$ over $|(target-actual)|$ [duplicate]

When computing loss functions, people use $(target-actual)^2$. They sqaure it to prevent any negative loss. But we can even use $|(target-actual)|$ to prevent any negative loss. So, why do people ...
Dhruv Agarwal's user avatar