Questions tagged [objective-functions]
For questions related to the concept of loss (or cost) function in the context of machine learning.
261 questions
0 votes
2 answers
79 views
What loss function to choose that will assign a higher penalty to false negatives than to false positives for regression task?
I am using a machine learning model to remove interference from range-doppler maps to detect targets. I am using a supervised approach, in which I give as input the range-doppler map of target+...
3 votes
1 answer
107 views
Universally better activation /loss function or specific-case dependency?
With the popularity of AIs from every media source this year,im interested in learning more about them and maybe one day build a good one.I have this code in python: ...
2 votes
1 answer
95 views
Are human content moderators needed anymore with AI?
Are human content moderators for social media websites needed anymore with AI? In other words, is AI so good now that it can detect if an image is pornographic, obscene, or in any violating social ...
0 votes
0 answers
85 views
how to use contrastive loss function for multi label classification?
I have a multi label classification problem, where I was initially using a binary cross entropy loss and my labels are one hot encoded. I found a paper similar to my application and have used ...
1 vote
1 answer
55 views
How can gradient descent optimize a loss surface that's never fully computed?
In gradient descent for neural networks, we optimize over a loss surface defined by our loss function L(W) where W represents the network weights. However, since there are infinitely many possible ...
0 votes
0 answers
45 views
How to write a custom loss for multi-label video classification?
I am trying to train a multi-label video classification model. My dataset consists of just one video, sampled at 1fps. I have a total of 12k frames and 21 classes, and in a single frame multiple ...
1 vote
1 answer
107 views
Loss function that penalizes errors more at low values
I am training Deep Learning models to predict the Remaining Useful Life (RUL) of certain devices. The RUL is an estimate of the time remaining until the device is expected to fail. Accurate ...
0 votes
0 answers
101 views
sudden NaN in the loss function of training a GAN for inpainting(AOT-GAN) I am sure there is no Nan in the input
I am now trying to train a GAN called AOT-GAN to do some inpainting operation on some anodized aluminium surfaces. At the beginning, I used a canon camera to take the photos for training the AOT-GAN....
1 vote
1 answer
158 views
Are these objective and loss functions from Actor-Critic Methods correct?
I'm doing a research about actor-critic methods and I want to make sure that I understand these methods right. First of all, I understand that as it's a combination of value-based and policy-based ...
1 vote
1 answer
102 views
Expected return formula for deterministic policy
I have a question regarding how the expected return of a deterministic policy in written. I have seen that in some cases the use the Q-Function as it is shown in the part Objective function ...
0 votes
0 answers
93 views
Loss function on intermediate layers of the networks
Typically in supervised learning, a neural networks' output is compared to the targets through a loss function, and the gradients are backpropagated. Is it a bad idea to also have a loss function on ...
2 votes
1 answer
65 views
Do we plug in the old values or the new values during the gradient descent update?
I have a scenario when I am trying to optimize a vector of D dimensions. Every component of the vector is dependent on other components according to a function such as: summation over (i,j): (1-e(x_i)(...
2 votes
1 answer
152 views
Custom Loss Function Traps Network in Local Optima
I am working with a feedforward neural network to fit the following simple function: N(1) = -1 N(2) = -1 N(3) = 1 N(4) = -1 But I don't want to use the Mean-...
0 votes
1 answer
145 views
Using conditional probability as an estimate in a loss function
I have a rather large ML framework that takes multiple conditional probability terms that are computed via classifiers/neural networks. This arbitrary loss function is computed via a function: ...
2 votes
0 answers
94 views
Can local learning rules minimize a global loss?
It is widely believed that synaptic plasticity is the way biological brains learn. Artificial implementations of this mechanism are for instance local weight-update rules in Spiking Neural Networks. ...