Questions tagged [objective-functions]
For questions related to the concept of loss (or cost) function in the context of machine learning.
259
questions
1
vote
1
answer
21
views
Multi-task objective sometimes improve single-task performance, but is this true when fine tuning?
It is known that multitask objectives in neural networks sometimes have the effect of improving the performance of the neural network for each of the tasks individually (versus training the same ...
2
votes
2
answers
37
views
Why does an action cost function dependes on result state in search problems?
In the famous AI book Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig (4th edition), in chapter 3, the action cost function of a problem solver agent denoted as $c(s, a, ...
2
votes
1
answer
60
views
Can you explain the Hinton's comment "Rprop is equivalent to using the gradient, but also dividing by the size of the gradient"?
Been reviewing some old foundational material and ran into this comment by Hinton on Rprop in his old Coursera class:
Rprop is equivalent to using the gradient, but also dividing by the
size of the ...
0
votes
0
answers
30
views
Non differentiable loss function train with actor critic style
I'm working on a project where a non differentiable loss is there. I'm thinking about how should I deal with them.
My model is a very big lstm model (about 1M parameter), and after 500 steps (not sure ...
0
votes
0
answers
151
views
What is the loss function used when pre-training BERT on MLM & NSP tasks?
I'm new to NLP and was reading through the 2019 BERT paper and am confused about the loss function used during pre-training.
As I understand it, the model is trained on the MLM and NSP tasks. The MLM ...
0
votes
0
answers
27
views
What Kind of Models and Loss Functions for User Churn Prevention by Promo Codes?
The Company Business Model
Bike rental with an app, where riders pay for the time they rented the bikes for.
The Business Case
User (rider) attrition prediction, and ideally, prevention. Basically, ...
0
votes
0
answers
29
views
Has There Been Research on Using a Neural Network as a Loss Function for Another Neural Network?
I'm intrigued by the idea of employing a separate neural network (which I'll refer to as the "loss network") to compute the loss for a primary network based on its inputs and outputs. The ...
1
vote
0
answers
32
views
How do LGBM rankers train?
I'm looking into Learning to Rank models - specifically, the LGBMRanker model - and I want to understand how it's able to train. It takes in features, group sizes and labels, and optimizes for a ...
1
vote
0
answers
23
views
Search recall optimization - what appropriate loss function to use?
I am studying machine learning and wanted to work on a project of my own so that I have better chances after graduating college. I'm studying the application of ML to improve searches using a toy ...
1
vote
1
answer
52
views
why learn an observation model when training latent space model in model based rl
I'm currently studying reinforcement learning through CS 285 provided by UC Berkeley.
At 1:52 of the part 5 of the lecture 11, I got confused on why one would want to learn an observation model $p(o_t ...
0
votes
0
answers
25
views
How to check clustering performance?
Background
I'm implementing the DBScan algorithm. I have trained it to cluster a small dataset of random clusters, and want to be able to get a decimal for its accuracy of clustering the groups.
...
0
votes
1
answer
90
views
In logistic regression, do I try to fit the graph perfectly or mimimize the error in the predicted probabilities?
In linear regression, I train the model so the graph runs best through the data points, so the geometric distance between f(x) and $y^i$ is minimized.
Now, is it correct that in logistic regression I ...
0
votes
0
answers
40
views
1
vote
0
answers
38
views
Can gradient descent cause loss to increase in some situations?
Is a gradient descent step always supposed to decrease loss? I can think of a situation where it would seem that gradient descent would increase loss but maybe it I am misunderstanding a part of ...
1
vote
2
answers
43
views
How do I assign a weight to an additional loss?
I am trying to do multi-spectral image fusion. I am using the following paper as a reference.
https://arxiv.org/pdf/1804.08361.pdf
The code available on GitHub works well. But, I am trying to add some ...
1
vote
0
answers
567
views
What is MLM & NSP loss function
Two objective functions are used during the BERT language
model pretraining step.
The first one is masked language
model (MLM) that randomly masks
15% of the
input tokens and the objective is to ...
4
votes
1
answer
329
views
What is the best way to combine or weight multiple losses with gradient descent?
I am optimizing a neural network with Adam using 3 different losses. Their scale is very different, and the current method is to either sum the losses and clip the gradient or to manually weight them ...
0
votes
1
answer
29
views
Which loss / activation function with 2 classes that do not occur often and do not sum to one?
I have a neural network that predicts 2 classes of a time series (bottom and top). Currenlty my Y labels are size 2: [1 0] for bottom and [0 1] for top. The NN has 2 output nodes.
Of course not every ...
0
votes
1
answer
312
views
What is the correct loss function for binary classification: Cross entropy or Binary cross entropy?
Let's say I have a binary classification problem and I want to solve it by means of FC neural net. So which approach will be correct: 1) define the last layer of NN like this ...
0
votes
1
answer
3k
views
What's the difference between classification and segmentation in deep learning?
What's the difference between classification and segmentation in deep learning?
In particular, can the classification loss function be used for segmentation problems?
2
votes
1
answer
126
views
Image classification problem with multiple right classes
I have a use case where the model needs to detect fabricdefects. There are 15+ different kinds of defects. In one image there can be multiple defects present. The straight forward solution for this ...
1
vote
1
answer
484
views
Why MSE and MAE yield poor results when used with gradient-based optimization for classification?
Deep learning book chapter 6: In 6.2.1.2 last paragraph:
Unfortunately, mean squared error and mean absolute error often lead to poor results when used with gradient-based optimization. Some output ...
0
votes
1
answer
104
views
Why is `SigmoidBinaryCrossEntropyLoss` in `DJL` implemented this way?
SigmoidBinaryCrossEntropyLoss implementation in DJL accepts two kinds of outputs from NNs:
where sigmoid activation has already been applied.
where raw NN output ...
1
vote
0
answers
35
views
Loss Function for Binary Classification with Multiple Correct Choices
I have a binary classification problem, where there are multiple correct predictions, however, I would consider the prediction to be correct if the highest confidence prediction of a 1 is correct.
I ...
0
votes
1
answer
47
views
Learning curve converges with huge errors
I am training an auto-encoder over $10^4$ epochs. I get a converging learning curve. However the error at the last stages stays huge $\sim10^{15}$. What does this mean? does it mean that my auto-...
1
vote
0
answers
73
views
Training a neural network simultaneously with two different loss functions rather than considering the weighted sum
This is a follow up on the already asked question: Is the neural network 100% accurate on training data if epoch loss is minimized to 0?
I want to train a neural network that works as an approximator ...
1
vote
0
answers
341
views
Left-to-Right vs Encoder-decoder Models
Xu et al. (2022) distinguishes between popular pre-training methods for language modeling: (see Section 2.1 PRETRAINING METHODS)
Left-to-Right:
Auto-regressive, Left-to-right models, predict the ...
1
vote
1
answer
57
views
Do we need to know or verify properties of loss functions / metrics' implementations?
I will start with an example, in order to get to the general question.
I was reading the following paper (https://www.cns.nyu.edu/pub/lcv/wang03-preprint.pdf) about Structural Similarity Index (SSIM), ...
0
votes
1
answer
163
views
Is the discriminator of a GAN network embedded in VAE?
From what I understand, a Generative Adversarial Network (GAN) is composed of an encoder (generator), some synthetic data (fake data) and a discriminator that will penalize any distinguishable real ...
3
votes
1
answer
214
views
What loss function should I use if I only care about the accuracy of one class?
CrossEntropyLoss optimizes the overall classification accuracy as
$$ {n_{\text{correct}} \over N} $$
What loss function should I use if I only care about increasing the true positive rate of one class?...
0
votes
2
answers
70
views
How to define a loss function for multi-label problem?
I have voice recordings which are labelled by not only a single label but multiple labels. Each voice recording corresponds to one of class labels within a set. In other words, the training instance ...
9
votes
1
answer
7k
views
What is the difference between the triplet loss and the contrastive loss?
What is the difference between the triplet loss and the contrastive loss?
They look same to me. I don't understand the nuances between the two. I have the following queries:
When to use what?
What ...
1
vote
2
answers
796
views
What should I think about when designing a custom loss function?
I'm trying to get my toy network to learn a sine wave.
I output (via tanh) a number between -1 and 1, and I want the network to minimise the following loss, where ...
1
vote
2
answers
342
views
What is the domain of the discriminator of a GAN?
I've read that the discriminator $D$ validates an image $D(x)$, where $x$ is either a real image or a fake one created by the generator, i.e. $ D(G(x))$.
What does the function of the discriminator ...
2
votes
0
answers
30
views
How to create a loss function that penalizes duplicate indices in the output tensor?
We're working on a sequence-to-sequence problem using pytorch, and are using cross-entropy to calculate the loss when comparing the output sequence to the target sequence. This works fine and ...
3
votes
1
answer
260
views
Why do we use "true labels" that are based on the output of our network in Deep Q-Learning?
In the original DQN paper, the $\ell_2$ loss is taken over the distance between our network output, $\hat{q}(s_j,a_j,w)$ and the labels $y_j=r_j+\gamma \cdot \max\limits_{a'} \hat{q}(s_{j+1},a',w^-)$, ...
1
vote
0
answers
41
views
Learning values in open ball: which final layers to employ?
I'm fairly new to deep learning and looking for some reference literature... Specifically, I want to train a neural network to predict vectors $v \in \mathbb{R}^3$ under the constraint $||v||\leq 1$.
...
0
votes
1
answer
82
views
How is catastrophic cancellation dealt with in loss functions?
It just occurred to me that this seems like it should be a very common problem that must have some kind of solution... Yet I'm not sure what it is...
If there is no solution, does this mean once a ...
0
votes
0
answers
71
views
how to define or calculate the similarity betweeen two curves as the loss funtion to optimize in the generative model?
I want to train a neural network as the curve productor that can generate the specific type of curves (e.g. exponential decay curves). I take the encoder-decoder structure, the curves in a dataset is ...
2
votes
1
answer
1k
views
What is the reason we loop over epochs when training a neural network?
After reading through this thread and some other resources online, I still do not understand the role of epochs in training a neural network. I understand that one epoch is one iteration through the ...
7
votes
2
answers
8k
views
What is the difference between a loss function and reward/penalty in Deep Reinforcement Learning?
In Deep Reinforcement Learning (DRL) I am having difficulties in understanding the difference between a Loss function, a reward/penalty and the integration of both in DRL.
Loss function: Given an ...
0
votes
0
answers
142
views
In CVAE's objective function, why do both terms condition on $\textbf{c}$?
I don't quite understand why, in Conditional Variational Autoencoder (CVAE), we concatenate a conditioning vector two times, at encoder and decoder respectively.
After we concatenate it once at the ...
0
votes
0
answers
60
views
How to reduce loss of Bi-LSTM handwriting recognition model?
I am currently training an bi-LSTM model which predicts the handwriting of an individual. I am hitting a current min loss of 1.2 and I think it is not a problem with the model because I copied a model ...
0
votes
1
answer
197
views
Does the summing or averaging of the weight gradients have anything to do with the cost function used?
I've been trying to implement my own neural network library and have been wondering if:
The SSE loss function includes the summation of the errors in the other training examples of the mini-batch (...
1
vote
1
answer
43
views
What inherent quality of a function makes it treated as either loss or evaluation metric?
A neural network model needs a loss function for training. The neural network needs to minimize the loss function.
A neural network is evaluated after training using a metric. The neural network needs ...
-1
votes
1
answer
215
views
Why is the cross-entropy a cost function?
The question looks foolish, but I think cross-entropy is somewhat weird as a cost function.
As a cost function for linear regression, the mean square error $ \sum_{i=1}^{n} (y_i - (ax_i+b)) ^2$ seems ...
3
votes
1
answer
139
views
Custom Tensorflow loss function that disincentivizes all black pixels
I'm training a Tensorflow model that receives an image and segments the image into foreground and background. That is, if the input image is w x h x 3, then the ...
1
vote
0
answers
85
views
a loss for binary step function data
I have some data with ground truth that looks like a binary step function, where part of it is 0 and part is one.
An example for the GT can be like ...
1
vote
0
answers
56
views
GANs: Why does iterative gradient descent sometimes optimise $\min_G \max_D V(D,G)$ and sometimes $\max_D \min_G V(D,G)$?
For the following minimax equation for generative adversarial networks (GANs),
$$\min_G \max_D V(D,G) = \mathbb{E}_{\boldsymbol{x}\sim p_{data}(\boldsymbol{x})}[\log D(\boldsymbol{x})] + \mathbb{E}_{\...
1
vote
1
answer
582
views
Why are logarithms used in GANs minimax equation?
The minimax equation for generative adversarial networks
$$\min_G \max_D V(D,G) = \mathbb{E}_{\boldsymbol{x}\sim p_{data}(\boldsymbol{x})}[\log D(\boldsymbol{x})] + \mathbb{E}_{\boldsymbol{z}\sim p_{\...