Questions tagged [loss-functions]

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

Filter by
Sorted by
Tagged with
1
vote
0answers
35 views

Add a layer derivative in the loss function

I am writing a NN in pytorch and I want to add the derivative of the output with respect to one of the inner layers in the loss. Here is a simple example of what I mean: ...
5
votes
3answers
202 views

Which function $(\hat{y} - y)^2$ or $(y - \hat{y})^2$ should I use to compute the gradient?

The MSE can be defined as $(\hat{y} - y)^2$, which should be equal to $(y - \hat{y})^2$, but I think their derivative is different, so I am confused of what derivative will I use for computing my ...
2
votes
2answers
86 views

How do we get the true value in the prediction objective in reinforcement learning?

In the book "Reinforcement Learning: An Introduction" (2018) Sutton and Barto define the prediction objective ($\overline{VE}$) as follows (page 199): $$\overline{VE}\doteq\sum_{s\epsilon S} \mu(s)[v_{...
1
vote
1answer
256 views

A2C Critic Loss Interpretation

I'm working on an Advantage A2C implementation, and I just finished creating the value network $\hat{V_{\phi}}$. I train this network with the standard MSE loss of discounted rewards-to-go:$$\|\hat{V_{...
1
vote
1answer
234 views

Train and Test Accuracy of GRU network not increasing after 2nd epoch

So I´m currently implementing my first neural network using GRUs as a model and Keras as an implementation since it´s pretty highlevel. My problem is about the classification of 8 hour long timeseries ...
2
votes
0answers
47 views

Should I use the hyperbolic distance loss in the case of Poincarè Disk Model?

I trained a neural network which makes a regression to a Poincarè Disk Model with radius $r = 1$. I want to optimize using the hyperbolic distance $$ \operatorname{arcosh} \left( 1 + \frac{2|pq|^2|...
6
votes
1answer
976 views

What's the advantage of log_softmax over softmax?

Previously I have learned that the softmax as the output layer coupled with the log-likelihood cost function (the same as the ...
5
votes
4answers
612 views

How to stop DQN Q function from increasing during learning?

Following the DQN algorithm with experience replay: Store transition $\left(\phi_{t}, a_{t}, r_{t}, \phi_{t+1}\right)$ in $D$ Sample random minibatch of transitions $\left(\phi_{j}, a_{j}, r_{j}, \...
3
votes
1answer
376 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 ...
1
vote
1answer
338 views

Understanding how the loss was calculated for the SQuAD task in BERT paper

In the BERT paper, section 4.2 covers the SQuAD training. From my understanding, there are two extra parameters trained, they are two vectors with the same dimension as the hidden size, so the same ...
7
votes
1answer
561 views

What loss function to use when labels are probabilities?

What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model. I want to train it with a feature vector $x=[x_1, x_2, \...
1
vote
1answer
696 views

Why isn't the reverse KL divergence commonly used in supervised learning?

Forward KL Divergence (also known as cross entropy loss) is a standard loss function in supervised learning problems. I understand why it is so: matching a known a trained distribution to a known ...
2
votes
1answer
277 views

Heavy loss and inaccurate answer in pytorch

As my first AI model I have decided to make an AI model to predict multiplication of two numbers EX - [2,4] = [8]. I wrote the following code, but the loss is very high, around thousands, and it's ...
2
votes
2answers
253 views

Why is MSE used over other quadratic loss functions?

So I was wondering, why I have only encountered square loss function also known as MSE. The only nice property of MSE I am so far aware of is its convex nature. But then all equations of the form $x^{...
1
vote
1answer
52 views

Which local minima to choose according to the shape of the error surface?

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. Considering the ...
4
votes
2answers
69 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 ...
2
votes
1answer
395 views

How do I get multiple loss per sample in keras evaluate? [closed]

Usually, when I evaluate() a model, I would get a single loss that is already averaged over all samples. How do I get the loss per each sample and return all of them? E.g. if my dataset has 100 ...
3
votes
1answer
149 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 ...
2
votes
2answers
816 views

Why am I getting spikes in the values of the loss function during training?

I trained a neural network on the UNSW-NB15 dataset, but, during training, I am getting spikes in the loss function. The algorithms see part of this UNSW dataset a single time. The loss function is ...
1
vote
1answer
107 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 ...
0
votes
1answer
455 views

Why is this PyTorch implementation of the actor-critic algorithm inconsistent with the mathematical formulas?

This PyTorch implementation of the actor-critic algorithm calculates the losses like so: ...
2
votes
1answer
88 views

Comparing and studying Loss Functions

I have a Deep Feedforward Neural Network $F: W \times \mathbb{R}^d \rightarrow \mathbb{R}^k$ (where $W$ is the space of the weights) with $L$ hidden layers, $m$ neurones per layer and ReLu activation. ...
3
votes
1answer
881 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 ...
1
vote
1answer
56 views

How do I calculate $max_{a′}Q(s′,a′,w−)$ when it is represented as a neural network?

Consider the following loss function $$ L(\mathbf{w}) = [(r + \gamma max_{a'} Q(s', a', \mathbf{w^-})) - Q(s, a, \mathbf{w})]^2 $$ where $Q(s, a, \mathbf{w^-})$ and $Q(s, a, \mathbf{w})$ are ...
0
votes
1answer
369 views

What is the derivative function used in backpropagration?

I'm learning AI, but this confuses me. The derivative function used in backpropagation is the derivative of activation function or the derivative of loss function? These terms are confusing: ...
1
vote
1answer
137 views

How can the sum of squared errors have negative gradient if it's defined as the squared of the error?

The formula for the sum of squared errors (SSE) is: $$ \frac{1}{2} \sum_{i=1}^n (t^i - o^i)^2 $$ I have a few related questions. If $t^i - o^i$ is negative, doesn't the power of 2 eliminate any ...
1
vote
1answer
27 views

Training by one batch of examples, what does it mean

Say I have a batch of examples, each examples represent a state: ...
5
votes
3answers
4k views

Can the mean squared error be negative?

I'm new to machine learning. I was watching a Prof. Andrew Ng's video about gradient descent from the machine learning online course. It said that we want our cost function (in this case, the mean ...
3
votes
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?
3
votes
1answer
503 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 ...
6
votes
2answers
1k views

How do we design a neural network such that the $L_1$ norm of the outputs is less than or equal to 1?

What are some ways to design a neural network with the restriction that the $L_1$ norm of the output values must be less than or equal to 1? In particular, how would I go about performing back-...
1
vote
1answer
74 views

How to understand marginal loglikelihood objective function as loss function (explanation of an article)?

I am reading article https://allenai.org/paper-appendix/emnlp2017-wt/ http://ai2-website.s3.amazonaws.com/publications/wikitables.pdf about training neural network and the loss function is mentioned ...
4
votes
1answer
81 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 $A$ ...
3
votes
1answer
2k 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 ...
11
votes
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 ...
3
votes
1answer
225 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 ...
2
votes
0answers
259 views

Extend the loss function from the single action to the n-action case per time step

My question concerns a side question (which was not answered) asked here: Policy gradients for multiple continuous actions I am trying to implement a simple policy gradient algorithm for a discrete ...
3
votes
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 ...
20
votes
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 ...

1 2 3
4