Questions tagged [objective-functions]
For questions related to the concept of loss (or cost) function in the context of machine learning.
212
questions
1
vote
0answers
41 views
What is the confusion loss for adversarial learning?
What is the confusion loss used in domain adaptation (DA) for adversarial learning/GANs? See this paper.
Two domains:
$s$: source domain
$t$: target domain
Generator/Discriminator setting:
$M_s:x_s\...
0
votes
0answers
25 views
Is there anything wrong with this YOLO loss function?
I have implemented the YOLOv1 loss function as:
...
1
vote
0answers
31 views
When can we call a loss function "adaptive"?
A loss function is a measure of how bad our neural network is. We can decrease the loss by proper training.
I came across the phrase "adaptive loss function" in several research papers. For ...
0
votes
0answers
25 views
Is there any significance for higher order gradients in artificial intelligence?
Although I don't know in detail, I am aware of the following facts regarding the usefulness of gradients in some domains of artificial intelligence, especially in optimization.
First order gradient: ...
0
votes
0answers
16 views
Do I need to imagine loss curves of changing shapes in case of GANs?
Loss function, in general, is imagined as a curve in higher dimensional space with weights on input axes and loss on output axes.
Suppose we have a neural network and we are training our neural ...
1
vote
1answer
62 views
Is there any difference between an objective function and a value function?
I found the usage of both objective function and value function in the same context.
Context #1: In the paper titled Generative Adversarial Nets
We simultaneously train G to minimize $\log(1 −D(G(z)))...
0
votes
1answer
41 views
Does average loss function in GAN training is just an approximation of value function and does not ensure convergence of generator and discriminator?
The value function on which convergence has been proved by the original paper of GAN is
$$\min_G \max_DV(D, G) = \mathbb{E}_{x ∼ P_{data}}[\log D(x)] + \mathbb{E}_{z ∼ p_z}[log (1 - D(G(z)))]$$
and ...
2
votes
2answers
55 views
How to check whether my loss function is convex or not?
Loss functions are useful in calculating loss and then we can update the weights of a neural network. The loss function is thus useful in training neural networks.
Consider the following excerpt from ...
3
votes
1answer
55 views
What are the necessary mathematical properties to be a loss function in gradient based optimizations?
Loss functions are used in training neural networks.
I am interested in knowing the mathematical properties that are necessary for a loss function to participate in gradient descent optimization.
I ...
0
votes
1answer
35 views
Why is the exponential loss used in this case?
I am reading a paper "Tracking-by-Segmentation With Online Gradient Boosting Decision Tree". In Section 2.1, the paper says
I cannot understand the exponential loss function. In my opinion, ...
2
votes
0answers
26 views
Is optimizing weighted sum multi objective tasks considered a multi-task learning?
I have two sequence prediction tasks, finding $\vec{\pi} \in \Pi$ and $\vec{\psi} \in \Psi$. Each sequence has its own objective function, i.e. $f_1(\vec{\pi})$ and $f_2(\vec{\psi})$. The input for ...
0
votes
0answers
22 views
Can people set loss function of neural network by themselves instead of choosing cross entropy or mean square error?
I found people used deep neural network to get optimal policy by solving a nonconvex optimization problem. Moreover, they didn't use any set of training data and claimed that it's the difference ...
0
votes
0answers
35 views
An explanation involving the sign activation, its affect on the loss function, and the perceptron and perceptron criterion: what is this saying? (#2)
I recently asked a very similar question here, but the answer only seems to address the first part of the quote, rather than the second part that contains the perceptron criterion example. Therefore, ...
1
vote
0answers
28 views
Is the formula $\frac {1}{s}\sum _{j=1}^{s}|d_{j}-y_{j}(t)|$ the correct form of 0-1 loss function, in the context of Perceptron?
Per page 7 of this MIT lecture notes, the original single-layer Perceptron uses 0-1 loss function.
Wikipedia uses
$${\displaystyle {\frac {1}{s}}\sum _{j=1}^{s}|d_{j}-y_{j}(t)|} \tag{1}$$
to denote ...
0
votes
0answers
11 views
Loss function to Push response value towards extremes
I have a feature map whose values are in the range of [0,1]. I want to push these values either towards extreme 0 or 1 using some loss function. Since I don't have any target value so it had to be in ...
0
votes
1answer
55 views
An explanation involving the sign activation, its affect on the loss function, and the perceptron and perceptron criterion: what is this saying?
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 says the following:
The classical activation ...
2
votes
1answer
94 views
In logistic regression, why is the binary cross-entropy loss function convex?
I am studying logistic regression for binary classification.
The loss function used is cross-entropy. For a given input $x$, if our model outputs $\hat{y}$ instead of $y$, the loss is given by
$$\text{...
3
votes
3answers
239 views
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 ...
0
votes
0answers
18 views
Good metrics and losses to use for Sequence-to-Sequence model for time-series prediction/forecasting
I am developing a sequence-to-sequence LSTM model for multi-step time series forecasting. I have the basic model working, so now I need to drill down on which loss function and evaluation metrics to ...
0
votes
0answers
19 views
Maximize delayed rewards
Given a Neural Network with a Dense(3) output and three actions:
'B' is [0, 0, 1] (= 1, for the sake of our example)
'N' is ...
2
votes
0answers
38 views
Loss function to minimize the distance between sets
Are there references or links to examples about loss functions "Distance Metrics" which could be used to minimize the distance between two sets for a neural network. More precisely, this ...
0
votes
0answers
23 views
Problems while transforming a 2D Variational Autoencoder into a 1D Version
I am trying to addapt the Keras variational autoencoder (VAE) here from a 2-D input/output (matrix of a picture) to a 1-D input/output (just a vector). I thought this would be a fearly easy task, but ...
0
votes
1answer
39 views
Which loss function could I use to solve a regression problem as a classification problem (where we discretize the labels into buckets)?
I am considering a rather typical regression problem, but, for practice, I am trying to implement this as a classification problem.
The setup is as follows. I have $\mathbb{R}$-valued labels $y_i \in [...
0
votes
0answers
27 views
How to improve the Loss and Learning curves and smoothen them
I am fairly new to deep learning and I have been testing out several architectures for the segmentation task of clouds in satellite imagery. I am using a simple Unet as my benchmark, Unet++, Efficient ...
0
votes
0answers
19 views
Defining optimal false-positives and false-negatives balance with a cost function
My attempt to solve the problem below:
$$\text{cost function} = C = (TP \cdot CTP) + (FN \cdot CFN) + (FP \cdot CFP) + (TN \cdot CTN) = ((1 - (1 - FP)^2) \cdot 1000) + (FN \cdot CFN) + (FP \cdot ...
0
votes
0answers
39 views
How is it possible that the softmax combined with the MSE in a molecule classification task performs than than the cross-entropy?
I'm working on a GNN project associated with molecule classification.
The project is to classify if the atom in the molecule will initiate a certain reaction.
For example, a molecule can be ...
0
votes
0answers
18 views
Training labels: integers or vectors?
I'm trying to implement Deep Q Learning using Tensorflow. The input is a vectorized representation of the state, and the output is a vector whose length is the number of possible actions.
I've already ...
0
votes
1answer
88 views
Why is loss displayed as a parabola in mean squared error with gradient descent?
I'm looking at the loss function: mean squared error with gradient descent in machine learning. I'm building a single-neuron network (perceptron) that outputs a linear number. For example:
Input * ...
1
vote
0answers
33 views
Could the inputs of the mean squared-error loss function be transformed to allow larger learning rates?
In the context of a neural network $\hat{y} = f_\theta(\mathbf{x})$ with parameters $\theta$ that is trained to perform regression such that the prediction $\hat{\mathbf{y}} = [\hat{y}_1,\hat{y}_2,...,...
0
votes
2answers
94 views
In variational autoencoders, why do people use MSE for the loss?
In VAEs, we try to maximize the ELBO $\mathbb(E_q log\ p(x|z) + D_{KL}(q(z|x), p(z))$), but I see that many implement the first term as MSE of the image and it's reconstruction. Is this mathematically ...
2
votes
1answer
57 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 ...
1
vote
1answer
51 views
Is the policy gradient expression in Fundamentals of Deep Learning wrong?
I don't understand the policy gradient as explained in Chapter-9 (Deep Reinforcement Learning) of the book Fundamentals of deep learning.
Here is the whole paragraph:
Policy Learning via Policy ...
1
vote
1answer
90 views
Why does the implementation of REINFORCE algorithm minimize the gradient term but not the loss?
I read the book "Foundation of Deep Reinforcement Learning, Laura Graesser and Wah Loon Keng", and when I go through the REINFORCE algorithm, they show the objective function:
$$
J\left(\...
1
vote
0answers
17 views
Is it normal getting noise values in the error history along training iteration?
I'm giving my first steps in really learning machine learning.
As an exercise in my online course, it was asked for me to code the Cost function of some neural network that should resolve the ...
0
votes
0answers
16 views
Do dataset sizes matter in a Style GAN?
When working with classifiers, a class imbalance is a huge issue for our models. If we have too many images of class 1 and too few images from ...
2
votes
0answers
56 views
How to deal with losses on different scales in multi-task learning?
Say I'm training a model for multiple tasks by trying to minimize sum of losses $L_1 + L_2$ via gradient descent.
If these losses are on a different scale, the one whose range is greater will dominate ...
0
votes
0answers
12 views
How to update all the weights in case only one data out of n signals is observable
If we have cost function as
$$E_i = (D_i -Y_i)^T Q (D_i -Y_i)$$,
where $$Q=\begin{bmatrix}
1 & 0 & 0\\
0 & 0 & 0\\
0 & 0 & 0
\end{bmatrix}$$( in case only one data signal can ...
0
votes
0answers
20 views
Gradient of CTC Loss?
I am having a hard time figuring out how the gradient of the CTC loss function looks like. Could anyone explain that to me?
0
votes
1answer
26 views
setting up last layer in tensoflow for class type of label [closed]
I am creating a NN in tensorflow keras. the inputs are all float and the output is a class.
The output currently encoded as a float, but only has 4 values (0,1,2,3).
My model is similar to this:
...
1
vote
0answers
56 views
BlackOut - ICLR 2016: need help understanding the cost function derivative
In the ICLR 2016 paper BlackOut: Speeding up Recurrent Neural Network Language Models with very Large Vocabularies, on page 3, for eq. 4:
$$ J_{ml}^s(\theta) = log \ p_{\theta}(w_i | s) $$
They have ...
0
votes
1answer
51 views
What error should I use for RNN?
I'm relatively new to machine learning, and I don't know what error I should use for an RNN.
I want to use a simple Elman RNN to predict the cases of Covid-19 there will be in a hospital for the next ...
2
votes
0answers
32 views
Single-value loss/training in a CNN with a tensor output
I am playing around with an idea of using using Q-learning with a DQN (Deep Q-Network), to determine the optimal position of a number of 'units' on a grid of allowed locations, according to some ...
3
votes
1answer
82 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 (...
1
vote
0answers
21 views
What does Dice Loss should receive in case of binary segmentation
I implemented Dice loss class in pytorch:
...
1
vote
0answers
43 views
How to make SAC (Soft-Actor-Critic) learn a policy?
I cannot make SAC learn a task in a certain environment. The point is that it actually sometimes finds a very good policy, but it never learns the policy in the end. I am using the SAC implementation ...
3
votes
1answer
208 views
What is the difference between a fitness function and a reward function?
In reinforcement learning (RL), the reward function (RF), which can be denoted as $r(s)$, $r(s, a)$, $r(s, a, s')$, $r(s, s')$ depending on its specific definition, provides the learning signal, which ...
1
vote
1answer
102 views
In this implementation of pix2pix, why are the weights for the discriminator and generator losses set to 1 and 100 respectively?
I am working on a pix2pix GAN model that was inspired by the code in this Github repository. The original code is working and I have already customized most of the code for my needs. However, there is ...
0
votes
1answer
104 views
When calculating the cost in deep Q-learning, do we use both the input and target states?
I just finished Andrew Ngs's deep learning specialization, but RL was not covered, so I don't know the basics of RL. So, I have been having trouble understanding the cost function in deep Q-learning. ...
0
votes
0answers
19 views
Which loss function should I use to train DDGP with multiple q values, one for each of the output dimensions?
I'm trying to come up with a loss function for the case, in DDPG, where we have as many outputs from the critic as there are from the actor. So, there will be one Q value for each dimension in the ...
1
vote
2answers
133 views
If the training data are linearly separable, which of the following $L(w)$ has less optimum answer for $w$, when $y = w^Tx$?
I'm studying machine learning and I came into a challenging question.
The answer is 2. But based on my ML notes, all of them are true. Where are the wrong points?
