Questions tagged [machine-learning]
Machine learning, a branch of artificial intelligence, is the science of getting computer systems to meaningfully act without being explicitly programmed by human.
125
questions
0
votes
0
answers
40
views
How can I calculate ROC50 in python?
I need to calculate ROC50 for a classifier in python. The ROC50 value is defined as the AUC when the 50th true negative is found. I have tried setting the max fpr value for roc_auc_score in sklearn to ...
- 101
0
votes
0
answers
31
views
OpenFOAM API: Access constructed matrix
I am interested in leveraging OpenFOAM to conduct data assimilation studies using 4DVar.
I already have CFD data, and I have synthetic measurement data. All I need to be able to do is to call OpenFOAM ...
- 101
2
votes
0
answers
66
views
Which class of PDEs is well-suited for multistep methods?
I am experimenting with machine learning techniques to solve partial differential equations (PDEs). My goal is to use solutions from previous time steps to predict the solution at the next time step, ...
- 169
0
votes
0
answers
10
views
Is the following the correct implementation of VGG network?
As exercise I am implementing few fundamental networks.
Specifically right now I am implementing VGG
The code I've got at the moment is the following:
class MyVGG(nn.Module):
...
- 163
11
votes
1
answer
343
views
Is it possible to express an arbitrary tensor contraction in terms of BLAS routines?
I noticed that libraries like numpy and pytorch are able to perform arbitrary tensor contractions at speeds similar to comparably sized matrix multiplications. This leads me to believe that underneath ...
- 121
0
votes
0
answers
24
views
dual svm square hinge loss
Let $x_1,\dots,x_n\in \mathbb{R}^n$, $y_1,\dots,y_n\in \{-1,1\}$, $\lambda \ge 0$
and $K$ be the invertible Gram matrix $K=(x_i\cdot x_j)_{ij}$.
Consider
$$
(P) \qquad \qquad \min_{a\in \mathbb{R}^n} \...
- 478
0
votes
0
answers
52
views
Nanograd differentation; what is going inside the python code
I am reading up on deep learning and I am trying to understand the backpropagation methods in python nanograd.
See; https://github.com/rasmusbergpalm/nanograd
This is a method for computing the ...
0
votes
0
answers
43
views
Verification of a Function Definition in Python
I want to write a function $f$ and it is defined as $f = - \nabla \cdot(|\nabla u|^{p-2} \nabla u) $ and I exact solution $u(x) = \tilde{u}(r) = 1 - \frac{p-1}{p-2} \left( s^{p/{p-1}} - (1-s)^{p/{p-1}}...
- 143
1
vote
0
answers
76
views
What architecture of CNN to solving a image regression problem (case study: solving Poisson equation)?
I've been working on solving Poisson problem using CNN model (you can ignore the Poisson problem part if you not familiar and jump to the image processing/CNN part). More specifically, I am solving ...
- 11
0
votes
1
answer
61
views
The row loss gradients
Suppose the original loss function is
$$\min_{\mathbf{V}}\frac{1}{2}\|\mathbf{V} - Q(\mathbf{V})\odot\mathbf{U}\mathbf{E} - \beta Q(\mathbf{V})\mathbf{V}\|_2^2$$
where $\odot$ denotes the element-wise ...
- 55
0
votes
1
answer
57
views
Dimensionality reduction between discrete wavelet families
I have what it may be a ridiculous question (since I don't know much about wavelets), but here I go.
I am using different Discrete Wavelet families to extract texture features from images. I plan to ...
- 3
12
votes
2
answers
1k
views
Faster Logistic Function
I've noticed that a fairly significant number of cycles in one of my programs are being consumed by the logistic function:
$$f(x)=\frac{1}{1+e^{-x}}$$
Is there a good approximation I can use to reduce ...
- 3,981
3
votes
1
answer
345
views
What problems does softmax() solve and when should I think of using it - in simple terms
I just for the first time saw the function softmax() in this SO answer to How do I use a minimization function in scipy with constraints and was intrigued.
Another way of weighting variables where ...
- 1,068
0
votes
1
answer
91
views
Does the loss function in a deep neural network act as a norm?
I read somewhere that the Measn squared error loss function acts as L2 norm of the paramter vector. I would like to know if I am using binary cross entropy loss function, do I need to calculate the ...
- 113
4
votes
0
answers
215
views
SINDy Vs standard methods for system identification
I have been trying to understand the recently proposed Sparse Identification of Nonlinear Dynamics SINDy. Despite several attempts, I seem to fail to understand the difference between SINDy and the ...
- 964