# Questions tagged [convolution]

Convolution is a function-valued operation on two functions $f$ and $g$: $\int _{-\infty }^{\infty }f(\tau )g(t-\tau )d\tau$. Often used for obtaining the density of a sum of independent random variables. This tag should also be used for the inverse operation of deconvolution. DO NOT use this tag for convolutional neural networks.

409 questions
Filter by
Sorted by
Tagged with
34 views
+50

### Mathematical representation of 1D convolution

How does one write the mathematical formula for conv1d used in PyTorch, including parameters like stride length and padding? For instance, I can write ...
38 views

### Spectral Graph Convolutions: What are the spectral filters functions

I am trying to understand the mathematical meaning of one of the steps that appear in the Convolution Theorem (Step 4 here). To give some context, this is related to applying the convolution theorem ...
46 views

### When is $\sum Z_i \sim \sqrt{n} Z_i$?

If $X_i$ are independently and identically distributed $N(0,\sigma^2)$ then $Y=\sum X_i \sim N(0,n\sigma^2)$, i.e. $\sum X_i \sim \sqrt{n}X_i$. That raises two questions: Is a zero-mean normal ...
8 views

### if i need a kernel to detect cones shape.. how to do so?

i'm working on a project of cones detection from lidar point cloud, I have got an idea to use Hough transform and I'm using convolution for voting principle for cone detection and I already ...
7 views

### A question about Convolutional Neural Networks, equivariance and parameter sharing

I have a couple of questions acbout Convolutional Neural Networks and I'm struggling to give an answer. Q1 Let's say I have $[3 \times 32 \times 32]$ image (with three channels) and I apply a first ...
24 views

### What is the best way to feed IMU data to CNN?

I took the Introduction to Embedded Machine Learning course, which is provided by Shawn Hymel, on Coursera. While talking about sensor fusion, he made the following statement for the following diagram:...
60 views

### Why CNN is suitable for time-series data? [duplicate]

I am confused by the statements that I came across in two different papers. The statement from the paper titled as "Detecting Cyber Attacks in Industrial Control Systems Using Convolutional ...
18 views

### Successor to Densenet, and Why Would My Resnet Model Peform Better Than My Densenet Model?

Currently, I'm modifying PoseNet, for use with camera localizaiton, with Resnet and Densenet. I modified both to have 2048 output classes, which feeds into dense layers to get the camera pose(like the ...
8 views

### Why does my loss decrease very slowing at the start of training, but picks up in the middle

I'm training S3D on my own dataset and uses a cosine learning rate decay. But the training loss doesn't decrease in the first 40 epochs, and than starts to decrease quickly, while the loss increased ...
12 views

### Do Convolutional Layers Pool data?

Sorry for the trivial question but considering this example in the image attached doesn't the conv layer pool data by summing them? What I am asking is if this images describes a subset where a conv ...
309 views

### Neural network to read short strings - translational invariance in CNNs

I have a series of short strings that each describe some item (one item per string). The people who write these strings can get pretty creative when it comes to spelling. For each string, I also have ...
11 views

### Recovering weights between neurons in a convolutional layer

Given a convolutional layer, I am interested in recovering the weight matrix $W$, where $w_{i,j}$ is the weight between neuron $i$ in the input layer and neuron $j$ in the output layer. I know that ...
26 views

### Calculating Convolution Only for a Certain Interval Using "conv()" in MATLAB

Below you can see the code for convolution of two continuous functions. There is a function called fx which I took as the square root of a Gaussian distribution. ...
95 views

### Convolution between two random variables

Given $X$ is a random variable which distributed uniformly in $[1,3]$ and $Y$ distributed uniformly in $[0,a]$. I need to calculate the value of the density function of: $$Z=X+Y,$$ at a point $b$ (i....
11 views

### CNN for images with different channel sizes

Assuming the channels of an image have different sizes. E.g.: red: 128x128, blue: 128x128, green: 256x256 Is it better to resize the green channel to a lower size, or would It be better to add a conv ...
97 views

### Does the sum of squared "dependent" Gaussian variables still exhibit a Chi-squared distribution?

Suppose we have $x_1,\cdots,x_n$, such that $x_i$ are i.i.d according to $x_i\sim N(0,1)$ for $i=1,\cdots,n$. Then we know that $Y=\sum_{i=1}^nx_i^2$ \begin{equation} Y\sim \chi^2(n) \end{equation} ...
20 views

### What is the resulting function to describe a log-normal function with Gaussian noise added?

I have a log-normal distribution: $\frac{1}{x} Ae^{-\frac{(ln(x)-\mu)^2}{2\sigma^2}}$ And I draw from it (1000 times) and plot the draws in a histogram: The log-normal function from which the draws ...
18 views

23 views

### What is the difference between the receptive field and a patch?

In this question and answer it is beautifully described what a patch is. What's a "patch" in CNN? However, for me, following the explanation in the link, it seems like a patch and the ...
Assume I have given independent, continous random variables $X_1, \ldots, X_n$ and assume that they all have support $[-\infty, \infty]$. If $X_1$ asymptotically dominates all others, i.e. $$f_{X_i}(\... 0answers 15 views ### Variance of DFT of filtered noise I am struggling with the following question: Let v(t) be a stationary stochastic process with Gaussian probability distribution and power spectral density S(\omega). Let the DFT of v(t) be V(k)=\... 0answers 42 views ### What could possibly be the reason why my CNN achieves abnormally high validation loss for some epochs? I am training a CNN for a simple binary classification problem and for some reason, I am getting abnormally high validation_loss at some epochs while still achieving good validation_accuracy. What am ... 0answers 16 views ### Autoencoder with feature maps as latent representation in TensorFlow - 3D voxel model reconstruction I am working on a 3D voxel model reconstruction network based on autoencoder architecture. I am using ResNet152v2 as encoder and then transposed 3D convolutional layers with stride = 2 and padding = &... 0answers 30 views ### Convolution formulation with central element of the Kernel matrix is superimposed on the pixel Suppose we perform the convolution operation with a Kernel of odd size. Suppose that the central element of the Kernel matrix is superimposed on the p-th pixel of the image being processed. Suppose: ... 1answer 44 views ### Can convolutional neural network learn integral operator? Given a function$$ u(x), x\in [0,1] $$Say 1D convolutional neural network, we all know it can learn the differential operator.$$ \partial u/ \partial x \approx D u  But what about the integral ...
Suppose that each in a set of $n$ random variables $\boldsymbol{X}_1, .., \boldsymbol{X}_n$ are Dirichlet-distributed with parameters $\boldsymbol{\alpha}_i$, where $i$ is an index for the random ...