konoha
Followers: 0 Following: 0
Feeds
已回答
how does stride work in denosing neural network
the first cnn layer has kernel [9 8]. This has scanned through the input matrix and output is a vector. a [1 100] works as desig...
how does stride work in denosing neural network
the first cnn layer has kernel [9 8]. This has scanned through the input matrix and output is a vector. a [1 100] works as desig...
2 years 前 | 0
提问
how does stride work in denosing neural network
I am studying the convolutional network in this article, https://www.mathworks.com/help/deeplearning/ug/denoise-speech-using-dee...
2 years 前 | 1 个回答 | 0
1
个回答提问
why does wavelet approximation need to multiply sqrt(2)
I am learning wavelet transform, the image below is one of my examples. Notices that when down sampling the sample signal, the a...
2 years 前 | 1 个回答 | 0
1
个回答提问
correct way visualize short time fourier transform on each window
I am trying to visulize the short time fourier transform by windows the code from below is what i have currently, but i am not ...
2 years 前 | 1 个回答 | 0
1
个回答已回答
construct wavelet function and its scaling function
cons_c = [1+sqrt(3), 3+sqrt(3), 3-sqrt(3), 1-sqrt(3)]/4; cons_w = [-(sqrt(3)-1), 3-sqrt(3), -(3+sqrt(3)), 1+sqrt(3)]/4; iters ...
construct wavelet function and its scaling function
cons_c = [1+sqrt(3), 3+sqrt(3), 3-sqrt(3), 1-sqrt(3)]/4; cons_w = [-(sqrt(3)-1), 3-sqrt(3), -(3+sqrt(3)), 1+sqrt(3)]/4; iters ...
3 years 前 | 0
| 已接受
提问
construct wavelet function and its scaling function
i am using the dilation equation to construct wavelet function and its scaling function. The process is simple, use Haar scaling...
3 years 前 | 1 个回答 | 0
1
个回答提问
denosing signal using wavedec and waverec
I am trying to use wavedec and waverec to denosing signals. suppose i have a signal x with some gaussian noise and then apply wa...
3 years 前 | 1 个回答 | 0
1
个回答提问
Denoise MNIST image with wavelet
I am learning wavelet and using it to denoise MNIST image with white noise, so far, the results i got are not pleasant. what can...
3 years 前 | 1 个回答 | 0
1
个回答提问
implementation of mini-batch stochastic gradient descent
I implemented a mini-batch stochastic gradien descent but counldn't find the bug in my code. I used this implement to do a clas...
3 years 前 | 2 个回答 | 0
2
个回答提问
question on elapsed time
I am working a problem that require to understand why each operation takes different time. So, I have a A = randn(100,100)...
8 years 前 | 2 个回答 | 0
2
个回答提问
use sound for a function
I have a function f(t) = sin(t) + sin(3t/2) + sin(5t/4) and I am trying to use sound for f. Fs=8000; Ts=1/Fs; t=[0:Ts:0...
8 years 前 | 1 个回答 | 0
1
个回答提问
compute Fast Fourier Transform matrix
I am trying to make a matrix like F = [1 1 1; 1 e^(1*2pi) e^(2*2pi); 1 e^(2*2pi) e^4*2pi], what I hav...
8 years 前 | 1 个回答 | 0
1
个回答提问
Use lsqnonlin to find the best angle of a linear transformation
I have a object=[1 0 0; 0 0 2], then it transforms to [0.9557 0.0965 0.9648; -0.3381 0.0158 1.8977] by a certain angle. I wan...
8 years 前 | 0 个回答 | 0
0
个回答提问
Using ode45 to solve second order differential system
I am trying to solve a system m_1x'' + k_1x = 0; m_2x'' + k_2x = 0, with m_1,m_2,k_1,k_2 are some constants. I read this po...
8 years 前 | 1 个回答 | 0
1
个回答提问
surface plot with a matrix
I am trying to graph a surface with a diagonal matrix, the equation I am trying graph is f = x^TDx, x is a 2 by 1 vector and D i...
8 years 前 | 1 个回答 | 0