# 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.

481 questions
Filter by
Sorted by
Tagged with
12 views

### Convolution problem [closed]

If the sum of coefficients of a filter h is zero, then for what padding will the sum of elements of a resultant convolved image also be zero after performing convolution with an image f(m,n) ?
11 views

### Why does convolutional neural network use a 2d Filter

Given an input of C,H,W where C is channels the filter is of size X,Y and slides across each channel individually. Why isn't the filter of size C,X,Y and slides across the entire 3d shape? I know of ...
• 236
51 views

### Deriving the pdf of noisy signal: sum of pdf f(s)=1/2+s/2 and a uniformly distributed noise [duplicate]

I am having a hard time to find the pdf of $\widetilde{s}=s+x$. $s$ has a pdf $f(s)=1/2+s/2$ where $s\in(-1,1)$. $x$ is uniformly distributed over $[-\epsilon, \epsilon]$. I am trying to use the ...
38 views

### Sampling line segments within a box

I'm at a bit of a loss for where to start with a sampling problem I'm having so any and all direction would be helpful. I essentially want to sample line segments of identical length within a bounding ...
• 31
343 views

### Distribution after Combining Two Sets of Normal Distribution Samples

Suppose I draw $N1$ samples from distribution $N(\mu_1,\sigma_1^2)$, $N2$ samples from distribution $N(\mu_2,\sigma_2^2)$. These two distributions are independent. Can the combined sample of $N1+N2$ ...
• 295
8 views

### Positional Invariance missing after max pooling operation in custom CNN

I am an early career researcher in computational neuroscience, and I am currently trying to model a robust object recognition model. My model takes a dataset (binary images; where each object is ...
21 views

### the Detailed Architecture of EfficientNetV2-B2

I'm currently studying different neural network architectures and I'm particularly interested in EfficientNetV2-B2. I understand that this model is an improved version of the original EfficientNet, ...
1 vote
26 views

### How should I go about completely decorrelating a digital signal?

So I'm working on real time signal compression, and I need to come up with the best convolution to minimize the entropy of incoming data (which I will then compress), which I understand is achieved by ...
• 11
135 views

### Uniform distribution over a triangle

Problem Consider a triangle $T$ with vertices $V_1,V_2,V_3 \in \mathbb{R}^2$ and let \begin{equation*}\begin{aligned} y&=z+v\\ v&\sim\mathcal{N}(0, R)\\ z&\sim\mathcal{U}(T) \end{aligned}\...
• 383
40 views

### Uniform density over 2 segments [duplicate]

Background Let $V_1, V_2 \in \mathbb{R}^2$ be the vertices of a segment and let $z$ be uniformly distributed over that segment. Now consider the random vector \begin{equation*} \begin{aligned} y&=...
• 383
99 views

### Convolution with a pathological distribution

Problem definition Consider the following random bivariate vector \begin{aligned} y&=z+v \\ z&\sim p_z(z;c) \\ v&\sim p_v(v) \end{aligned} where $p_z$ ...
• 383
1 vote
13 views

### Why does GAP at the end of FCN for MTSC work?

I have a binary MTSC (Multivariate Time Series Classification) problem where i train a CNN, namely a FCN (or Fully Convolutional Network) to predict class 0 or class 1 based on a multivariate time ...
• 11
1 vote
51 views

### Percentiles of a distribution of weighted summary statistics

Suppose I have a collection of different independent probability distributions, $\{ P_i(X)\}_{i=1}^N$, each with their own support $I_i$. I know that the $10^{th}$ percentile of a given distribution ...
• 159
247 views

### What is the variance of convolution of two random variables?

Consider two random variables $Z$ and $W$. Given the variances of $Z$ and $W$, how can we compute the variance of their convolution $Z \circledast W$? As an example, please consider the case of noise ...
27 views

### PDF of difference of uniform distributions [duplicate]

Main questions are in bold but feel free to correct me if I'm wrong somewhere else. As far as possible, I need both intuition and formal explanation. Let $X \sim Uniform(a,b)$ and $Y \sim Uniform(c,d)$...
2k views

### Probability that sum of binary variables is even

Let $S_i \in \{0,1\}$, $i=1,\dots,N$ be $N$ independent random binary variables, each taking the value 1 with probability $0 \le p_i \le 1$ (and the value 0 with probability $1-p_i$). I am interested ...
• 4,480
1 vote
24 views

### What is the distribution of a RV with the constant random variable? [duplicate]

For random variables (rv) $X$ and $Y$ on a space $\Omega$: Assume the rv $X\sim f_0$ distributed and $Y(t)=c$ is a constant rv, i.e. $Y\sim \delta(t-c)$ using the $\delta$-distribution as a short ...
• 209
76 views

### Why is the maximum path length for convolutional layer $O(n/k)$ in attention is all you need paper?

In the table-1 third row it is being mentioned. Why is it $O(n/k)$? Take for example 1d convolution of 2 over 9 tokens with stride $1$. It won't be $n/k$ or $9/2=4.5$ rather it would be roughly $n-1$ ...
15 views

### Inference on latent variable with observation of its convolution with itself

Problem I have an inference problem where the data observed are univariate random numbers whose distribution is obtained as follows. A latent random variable X is first sampled from a parametric ...
43 views

### Weighted Average of Uniformly Distributed RV [duplicate]

Let $x \sim U[0,1]$ and $y\sim U[0,1]$. Let $z= \omega\, x+ (1-\omega)\,y$, where $\omega\in[0,1]$. The pdf of $z$ is a trapezoidal distribution over $[0,1]$: \begin{equation*} \begin{aligned} f(z)&...
1 vote
113 views

### Convolutional Neural Networks - Flattening with multiple feature maps

I have a very simple question about CNNs, which I unfortunately couldn't find an explanation for. Imagine we have a CNN, that has four filters (eg right, left, top, bottom edges) each of those outputs ...
142 views

### How to obtain the last convolutional layer of a model in torchvision for applying grad cam?

I'm using efficient net b0 from torchvision for training a classifier for cifar10. I would like to apply grad cam for generating saliency maps for explaining the predictions. However, I'm not sure ...
• 1,008
23 views

### Computing an integral that reduces to $\mathbb{P}[X>Y]$

Problem Evaluate $$I=\int_{-\infty}^\infty \frac{e^{-\frac{1}{2}\left(\frac{x-\mu)}{\sigma} \right)^2}}{\sigma \sqrt{2 \pi}}\frac{1}{1+e^{-x}}\, \mathrm{d}x$$ My attempt Now the first part of the ...
22 views

### Exact Successor State Distribution for a Pendulum

I want to solve the following problem. Suppose we have a simple pendulum, which follows the differential equation \dot{x} = f(x) = [x_2, -\sin(x_1)]^T, \text{with } x=[x_1, x_2]^T. \...
• 307
41 views

### No activation function between two convolutional layers in MUNIT?

I'm reading the code of NVIDIA's MUNIT, the code of the resnet is as follows: ...
• 21
1 vote
205 views

24 views

### Cannot apply simple OLS model in the case of low resolution devices resulting in Fourier space convolution

There's a problem which often comes up within my field and doesn't seem to be approachable analytically. Any suggestions or direction towards the class of problems this falls under would be helpful. ...
• 1
1 vote
184 views

### When is a conditional hazard rate increasing?

Cross posted from Mathoverflow Let $X$ and $Y$ be two random variables such that $X\sim Exp(\lambda)$ and $Y$ have positive support and (strictly) increasing hazard rate $h_Y$. $X$ and $Y$ are ...
134 views

### Convolution of two functions doesn't fit my data as I thought it would

I have simulated a Gaussian curve in 50 bins of data. I have then repeated this many times, drawing the amplitude of the Gaussian from a log-normal distribution. Here are a 10 realizations: (IMAGE 1) ...
• 1,233
50 views

### Estimating the distribution of a sum of two random variables if the family of one of the variables is known

Assume I have a random variable $Y=X_1+X_2$. I want to estimate the distribution $f$ of $Y$ given a sample $y_1,\ldots,y_N$. If this was all that is known about $Y$ the best way would probably be to ...
• 2,671
127 views

• 133
84 views

### what are the differences between receptive field (RF) and field-of-views (FOV) in DeepLab papers?

I am learning the deeplab models. However, some concepts in the papers made me confused. Receptive field (RF) and field-of-views (FOV) are two concepts mentioned in the Deeplabv1 paper. I know that ...
• 311
375 views

### Density of $|t_1 - t_2|$ where $t_1$ and $t_2$ are iid with $P(t) = \alpha e^{-t\alpha}$

I am trying to answer the following question from my quantum mechanics textbook and my probability theory is admittedly rusty (this is not schoolwork as should be clear from my post history on Phys ...
• 203
1 vote
70 views

### Order Statistics - Percentile Range of Normal Mixture of Normals

Say I have draw N values from a normal distribution [$\mu_1$, $\sigma_1$]. Below are 10 sampled points compared to the normal distribution they're sampled from I then create a normal mixture of ...
118 views

### Distribution closed under convolution and truncation followed by convolution

Let $D(\theta)$ denote an absolutely continuous distribution on $\mathbb{R}$. (The finite dimensional vector $\theta$ collects the parameters of the distribution.) Assume that the p.d.f. of $D(\theta)$...
• 525
1 vote
216 views

### How can I build a 6D Convolution Layer in a CNN, using R or Python? [closed]

As stated in the title, I would like to build an N-dimensional Convolutional Layer as part of a Convolution Neural Network, without doing dimensionality reduction on my data; because I have multiple ...
• 113
26 views

### Unclear Architecture of MNIST Neural Network

I am trying to reproduce a Neural Network trained to detect whether there is a 0-3 digit in an image with another confounding image. The paper I am following lists the corresponding architecture: A ...
1 vote
93 views

### What "Convolution filters along the time axis" means?

Suppose that I have a tensor of height:25 and width:50. Height is my temporal axis, therefore I have a window of 25 time steps. Therefore my input tensor is: I want to extract temporal features / ...
• 233
1 vote
42 views

### Relationship between convolutions in neural nets and probabilistic convolution

In probability theory, convolution extends to produce the distribution of the sum of two independent random variables. I've only ever seen this in the context of univariate random variables. However, ...
• 319
1 vote
14 views

### Are Class Activated Maps an example of backpropagated Explainable AI?

Class Activated Maps (NOT GradCAM) is listed in van der Velden et al as a back-propagation approach in table 1, but that is not actually true, is it? CAM doesn't use back-propagation in the method, ...
1 vote
23 views

### How to calculate how much each error source contributes to an overall accuracy metric?

I am building a model of overall accuracy for a robotic system, I have various error sources from assembly, calibrations, measurements, imaging, for each error I have a PDF of the error it induces on ...
114 views

### How to average multiple non-normal distributions?

I have the following statistics of two independent random variables: First random variable: ...
• 39
1 vote
42 views

### Mean conditional on sum

Let $X$ and $Y$ be two random variables. I am interested in how $\mathrm{E}[X | X + Y = z]$ changes as $z$ changes. Intuitively, if $X$ and $Y$ are independent, the conditional mean should be ...
I am trying to do: find 1000 points that represent samples from distribution X with parameters $(a,b,c,\ldots, d)$ be guaranteed that the MLEs for those 1000 points are $(a,b,c,\ldots, d)$ with $99\%$...