# Questions tagged [loss-functions]

For questions related to the concept of loss (or cost) function in the context of machine learning.

198 questions
Filter by
Sorted by
Tagged with
3answers
25k views

### How can we process the data from both the true distribution and the generator?

I'm struggling to understand the GAN loss function as provided in Understanding Generative Adversarial Networks (a blog post written by Daniel Seita). In the standard cross-entropy loss, we have an ...
1answer
4k views

### Loss jumps abruptly when I decay the learning rate with Adam optimizer in PyTorch

I'm training an auto-encoder network with Adam optimizer (with amsgrad=True) and ...
1answer
590 views

1answer
90 views

### How to define a loss function for a classifier where the confusion between some classes is more important than the confusion between others?

I have a dataset of images belonging to $N$ classes, $A_1, A_2...A_n,B_1,B_2...B_m$ and I want to train a CNN to classify them. The classes can be considered as subclasses of two broader classes $A$ ...
1answer
299 views

### How should we interpret this figure that relates the perceptron criterion and the hinge loss?

I am currently studying the textbook Neural Networks and Deep Learning by Charu C. Aggarwal. Chapter 1.2.1.2 Relationship with Support Vector Machines says the following: The perceptron criterion is ...
2answers
70 views

### Could error surface shape be useful to detect which local minima is better for generalization?

The following plot shows error function output based on system weights. Two equal local minima are shown in green pointers. Note that the red dots are not related to the question. Does the right one ...
1answer
238 views

### Why is the evidence equal to the KL divergence plus the loss?

Why is the equation $$\log p_{\theta}(x^1,...,x^N)=D_{KL}(q_{\theta}(z|x^i)||p_{\phi}(z|x^i))+\mathbb{L}(\phi,\theta;x^i)$$ true, where $x^i$ are data points and $z$ are latent variables? I was ...
1answer
50 views

### Why is the mean used to compute the expectation in the GAN loss?

From Goodfellow et al. (2014), we have the adversarial loss:  \min_G \, \max_D V (D, G) = \mathbb{E}_{x∼p_{data}(x)} \, [\log \, D(x)] \\ \quad\quad\quad\quad\quad\quad\quad + \, \mathbb{E}_{z∼p_z(...
1answer
124 views

### Is there a reason to choose regular momentum over Nesterov momentum for neural networks?

I've been reading about Nesterov momentum from here and it seems like a nice improvement over regular momentum with no extra cost whatsoever. However, is this really the case? Are there instances ...
1answer
79 views

### What is the cost function of a transformer?

The paper Attention Is All You Need describes the transformer architecture that has an encoder and a decoder. However, I wasn't clear on what the cost function to minimize is for such an architecture. ...
1answer
1k views

### What's the difference between RMSE and Euclidean distance, and when to use a custom loss? [closed]

I'm searching for a loss function that fits my project. Actually, I have two questions, but they are in the same direction. I take a look at the definition of the root mean squared error (RMSE) and ...
1answer
51 views

### How to add weights to one specific input feature to ensure fair training in the network?

I am trying to create a multiclass product-rating network based on product reviews and other input features. Two of the other input features are "product category" and "gender". However, I want to ...
2answers
526 views

### Why does TensorFlow docs discourage using softmax as activation for the last layer?

The beginner colab example for tensorflow states: Note: It is possible to bake this tf.nn.softmax in as the activation function for the last layer of the network....
1answer
300 views

### Why does the binary cross-entropy work better than categorical cross-entropy in a multi-class single label problem?

I was just doing a simple NN example with the fashion MNIST dataset, where I was getting 97% accuracy, when I noticed that I was using Binary cross-entropy instead of categorical cross-entropy by ...
0answers
28 views

### How do weights changes handles during back-propagation when there are unknown labels

I have a question about how weights are updated during back-propagation for some of my samples that have unknown labels (please note, unknown, not missing). The reason they are unknown is because this ...
3answers
2k views

### In which cases is the categorical cross-entropy better than the mean squared error?

In my code, I usually use the mean squared error (MSE), but the TensorFlow tutorials always use the categorical cross-entropy (CCE). Is the CCE loss function better than MSE? Or is it better only in ...
3answers
735 views

### What's the function that SGD takes to calculate the gradient?

I'm struggling to fully understand the stochastic gradient descent algorithm. I know that gradient descent allows you to find the local minimum of a function. What I don't know is what exactly that ...
2answers
141 views

### How to obtain a formula for loss, when given an iterative update rule in gradient descent?

From the reinforcement learning book section 13.3: Using pytorch, I need to calculate a loss, and then the gradient is calculated internally. How to obtain the loss from equations which are stated ...
1answer
8k views

### What is an objective function?

Local search algorithms are useful for solving pure optimization problems, in which the aim is to find the best state according to an objective function. My question is what is the objective function?
1answer
72 views

### How to incorporate a symmetry constraint in the loss function to train a CNN?

I have a task of extremely sparse binary segmentation, i.e. the segmentation mask contains either 0 or 1, and there are ~95% zeros and only ~5% ones. I use the focal loss to address the sparseness (...
1answer
1k views

### Are the training loss and validation loss plotted per sample or per batch?

I am using a CNN to train on some data, where training size = 21700 samples, and test size is 653 samples, and say I am using a batch_size of 500 (I am accounting for samples out of batch size as well)...
2answers
64 views

### If loss reduction means model improvement, why doesn't accuracy increase?

Problem Statement I've built a classifier to classify a dataset consisting of n samples and four classes of data. To this end, I've used pre-trained VGG-19, pre-trained Alexnet and even LeNet (with ...
1answer
420 views

### Alphazero policy head loss not decreasing

I am now working on training an alphazero player for a board game. The implementation of board game is mine, MCTS for alphazero was taken elsewhere. Due to complexity of the game, it takes a much ...
1answer
157 views

### How is equation 8 derived in the paper “Self-critical sequence training for image captioning”?

In the paper "Self-critical sequence training for image captioning", on page 3, they define the loss function (of the parameters $\theta$) of an image captioning system as the negative expected reward ...
1answer
543 views

### Chess policy network

I am interested in making a simple chess engine using neural networks. I already have a fairly good value network but I can't figure out how to train a policy network. I know that Leela chess zero ...
1answer
2k views

### Why is the hyperbolic tangent with MSE better than the sigmoid with cross-entropy?

Usually, in binary classification problems, we use sigmoid as the activation function of the last layer plus the binary cross-entropy as cost function. However, I have already experienced (more than ...
1answer
1k views

### Advantages of Kullback-Leibler over L1/L2?

I've recently encounter different articles that are recommending to use KL instead of L1/L2 norm when trying to minimize a probability distribution. But none of the articles are giving a clear ...
1answer
550 views

### Which loss function should I use for binary classification?

I plan to create a neural network using Python, Keras and TensorFlow. All the tutorials I have seen so far are concerned with image recognition. However, the goal of my program would be to take in 10+ ...
1answer
982 views

### Dice loss gives binary output whereas binary crossentropy produces probability output map

On recommendation of Kanak on stackoverflow I am posting this question here: Currently I am experimenting with various loss functions and optimizers for my binary image segmentation problem. The loss ...
1answer
3k views

### How do I calculate the gradient of the hinge loss function?

With reference to the research paper entitled Sentiment Embeddings with Applications to Sentiment Analysis, I am trying to implement its sentiment ranking model in Python, for which I am required to ...
1answer
234 views

### Should the input to the negative log likelihood loss function be probabilities?

I am trying to train a supervised model where the output from the model is output of a linear function $WX + b$. Kindly note that I'm not using any softmax or $\log$ softmax on the result of the ...
0answers
35 views

### Enforcing sparsity constraints that make use of spatial contiguity

I have a deep learning network that outputs grayscale image reconstructions. In addition to good reconstruction performance (measured through mean squared error or some other measure like psnr), I ...
1answer
119 views

### When should I create a custom loss function?

I'm using a neural network to solve a multi regression problem because I'm trying to predict continuous values. To be more specific, I'm making a tracking algorithm to track the position of an object, ...
1answer
75 views

### When to use RMSE as opposed to MSE and vice versa?

I understand that RMSE is just the square root of MSE. Generally, as far as I have seen, people seem to use MSE as a loss function and RMSE for evaluation purposes, since it exactly gives you the ...
0answers
204 views

### Understanding log probabilities of actions in the PPO objective

I'm trying to implement the Proximal Policy Optimization (PPO) algorithm (code here), but I am confused about certain concepts. What is the correct way to implement log probability of a policy (...
3answers
153 views

### How do you interpret this learning curve?

Loss is MSE; orange is validation loss, blue training loss. The task is NN regression (18 inputs, 2 outputs), one layer 300 hidden units. Tuning the lr, mom, l2 regularization parameters this is the ...
3answers
145 views
+50

### Where does the so-called 'loss' / 'loss function' fit into the idea of a perceptron / artificial neuron (as presented in the figure)?

I am currently studying the textbook Neural Networks and Deep Learning by Charu C. Aggarwal. Chapter 1.2.1.3 Choice of Activation and Loss Functions presents the following figure: $\overline{X}$ is ...
1answer
94 views

### Should illegal moves be excluded from loss calculation in DQN algorithm?

I'm implementing DQN algorithm to train my agent to play a turn-based game. The action space for the game is small, but not all moves are available at all the states. Therefore, when deciding on which ...
2answers
854 views

### What are the major differences between cost, loss, error, fitness, utility, objective, criterion functions?

I find the terms cost, loss, error, fitness, utility, objective, criterion functions to be interchangeable, but any kind of minor difference explained is appreciated.
1answer
52 views

### Is it possible to use an internal layer's outputs in a loss function?

For a network of the form: Input(10) Dense(200) Dense(100+10) Dense(20) Output() Those +10 outputs are what I want to add to ...