Questions tagged [deep-learning]
The deep-learning tag has no summary.
94 questions
0 votes
0 answers
49 views
How do calculate the number of learning parameters in deep learning networks?
I have run the example in the link in the following two cases: Case 1: NumHeads = 4, NumKeyChannels = 784 Case 2: NumHeads = 8, NumKeyChannels = 392 Note that: <...
- 349
2 votes
0 answers
33 views
How can a course on digital image processing supplement a standard course on machine learning?
I've never been taught a course on digital image processing. I only know that 2D Fourier transform, 2D convolution, Gabor filter, edge detection, etc., are some interesting topics in this subject. ...
0 votes
1 answer
74 views
Implications of adding gaussian noise after denoising original signal
I'm new to DSP due to a research project related with audio classification. We are designing a DL-based pipeline to determinate which kind of vessel appears in underwater recordings. Thing is that I'...
- 3
1 vote
0 answers
157 views
What features can be used to estimate both azimuth and elevation angle using a deep learning model?
I am trying to estimate both azimuth and elevation angle, for which I simulated a URA, whose code is given below. ...
- 173
0 votes
1 answer
110 views
What is the best to add accelerometer noise to PPG signals?
I have a BIDMC PPG signals. I'm trying to add accelerometer data as a noise to PPG signals and trying to denoise it using deep generative models like GANs, VAEs, Diffusion Models. So, what can be the ...
0 votes
1 answer
206 views
How to mask part of signal?
I am trying to implement masking in 1D signal data, I saw in one paper that they are masking 70% of the signal as in the figure below: In another study, they have mentioned that the mask part is ...
- 163
0 votes
0 answers
55 views
Segmenting audio in its different parts using deep learning
I am trying to segment a song into its different parts. In pop music, it's common for a song to have a verse and a chorus. And they repeat. So it should be possible to use deep learning to find the ...
- 1
1 vote
1 answer
70 views
preparing the ct scan data of a patient, using a visible feature in the mri image
A dataset of mri and ct scan images of patients has been prepared. There is a feature /damaged area/ in the mri image that is easily visible. But the injury of this area is not visible in the CT scan ...
- 11