Questions tagged [neural-network]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
6
votes
3answers
3k views

Neural Networks and Complex Valued Inputs

[not sure if this or stats.stackexchange was the correct location for this post, so put it on both for now.] I've seen some recent papers describing complex valued neural networks like this one: Deep ...
4
votes
2answers
8k views

Can deep neural networks achieve real-time video analysis?

Recently, convolutional neural network based, deep architectures (DNN) such as AlexNet and VGGnet have been very successful in image classification challenges (e.g. ImageNet) and action recognition/...
4
votes
1answer
3k views

Spectrograms for neural nets

General Question Given an audio file, say a 16-bit wav, what are some standard methods to preprocess a spectrogram of this wav so that it may be fed into a neural net? Context In Lee et al's 2009 ...
4
votes
1answer
317 views

“Bi Directional” Kalman Filter

I am working on a project in Object Tracking, i.e. need to predict the location of next bounding box. I used a Hungarian algorithm with a Kalman Filter (which is a common method in this domain) which ...
4
votes
4answers
239 views

After advice about detecting focus quality of objects in a photo detected using YoloV3

I've spent the last couple of days playing with YoloV3, and have had very good results. My use case is sports photography, and the object detection for people/bikes etc is very very good, I'm very ...
3
votes
1answer
38 views

Perform Transposed Convolution in Spectral / Frequency Domain?

I'm doing some experimentation on performing end to end generative modeling in the frequency domain. I've got a working convolutional layer, but do not yet have a Conv2DTranspose equivalent. Please ...
3
votes
1answer
41 views

The Meaning of $ \mathbb{E} $ Operator in the Pix2Pix Loss Formula of a Neural Network / Convolutional Neural Network

I've been observing the Pix2Pix Paper - Image to Image Translation with Conditional Adversarial Networks and wondered on formulas. For example, the objective of the CGAN is: , where x - observed image,...
3
votes
3answers
5k views

Principal Component Analysis (PCA) on Convolutional Neural Network (CNN) Features

Please, I have a question regarding PCA and features which are extracted from a convolutional layer. link if we have a test dataset , and we extract all conv features of all images at test dataset ...
2
votes
2answers
470 views

Does an equivalent transformation of a signal to a spectrogram image exist in which the phase information is part of the resulting image?

I'm working on a research project where we would like to apply convolutional neural networks to an image representation of a signal. However, it seems that if I would use a spectrogram, I would end up ...
2
votes
1answer
480 views

Upsampling vs downsampling. Which to use when?

Downsampling reduces dimensionality of the features while losing some information. It saves computation. Upsampling brings back the resolution to the resolution of previous layer. My question is which ...
2
votes
1answer
83 views

Deriving the Langrangian interpolation polynomials in Cook-Toom convolutions

I'm working through Blahut's 'Fast Algorithms for Signal Processing'. Trying to develop an intuition for the Cook-Toom algorithm for convolutions as used by Lavin and Gray in their Winograd paper for ...
2
votes
1answer
257 views

How to Remove the Patch Artifacts of Neural Network Denoising Process?

I have written a python script which uses the Noise2Noise: Learning Image Restoration without Clean Data implementation of the Auto Encoder which is useful to remove noise from images. In the original ...
2
votes
1answer
1k views

What is the best input for de-noising autoencoder for sound data?

I am currently trying to build an autoencoder to de-noise audio data. However I have not found any good articles explaining about the input to the autoencoder, i.e. feature vector. As in speech ...
2
votes
1answer
2k views

Downsampling audio for use in Machine Learning

I'm trying to use the work (Neural Networks) done in this repo: https://github.com/jtkim-kaist/VAD It says this: Note: To apply this toolkit to other speech data, the speech data should be ...
2
votes
1answer
181 views

identify a specific table in document image

I have some images of answered tests. I am working on recognizing the answers for the multiple choice questions on each test. A example: I think the problem can be separate into two sub-problems: ...
1
vote
1answer
60 views

a neural network approach for FIR filter

I am trying to write a code for a neural network to do the digital filtering on some signals. Is there any neural network model for digital filtering?
1
vote
1answer
4k views

Convolution and Cross Correlation on 2D Image

I have read that convolution and cross-correlation are the same thing, but convolution flips 180 degrees (images), or time reverses (sequences) the kernel, before performing the elementwise ...
1
vote
1answer
79 views

In Convolutional Neural Nets, what do convolutions look like?

The early stages of the Convolutional Neural Networks are performing classical convolutions with a certain kernel size on the input image. Is is possible to express in common terms the type of ...
1
vote
1answer
421 views

Pattern recognition in time series 4x3000 vector

I have a vector, here is a sample of some data from some heat flow data: I would like to identify features in this image. In the example above I have identified one feature I would like to ...
1
vote
1answer
546 views

What would the target matrix to train Neural Network?

I'm new at Artificial Neural Network and I'm using MATLAB developing Facial expression recognition and There are six expressions ; I'm not able to understand about How to create a target matrix? My ...
1
vote
1answer
29 views

FFT question as it relates to Neural Networks / Supervised Learning Models

So I've been researching wavelet transforms and FFT. I want to feed wavelet transforms of a 1D signal in time into a neural net and train against a target variable at each time step. The idea being ...
1
vote
1answer
69 views

Neural networks in system identification - What type of activation functions?

I made a free software for all operative systems, even Android. It's called Deeplearning2C. It can train a neural network and generate C code and MATLAB-code. C-code for embedded systems and MATLAB-...
1
vote
1answer
393 views

Generate audio data using VAE+GAN

I am trying to train a VAE+GAN model to generate sounds produced by honeybees. I build my model by slightly modifying this tutorial, which aims to generate new MNIST images. Since my data are 1D ...
1
vote
1answer
62 views

Good Reference Problem to Test Filtering/Estimation Algorithms

I am looking to figure out if a current filter algorithm I have built could be useful for some problems I am looking into at work. It isn't a Kalman filter, but is instead making estimations using a ...
1
vote
1answer
550 views

Delay issue in time series prediction

I am having an issue using neural networks to predict time series. Some predicted data fits with the expected data, as bellow: (In black the real time series and in blue the output of my neural ...
1
vote
0answers
87 views

Image from Inverse FFT operation is sparse

I'm trying to train a deep nerual network that takes in input, an signal in the frequency domain, and attempts to learn a mapping to another signal in the frequency domain. Basically, the input to ...
1
vote
0answers
81 views

Neural Networks for rotated character (or shape) recognition

I have built a program that recognizes shapes and characters, using Neural Networks. Now, one of the main requirements of the task is that the program can recognize them regardless of rotation or ...
1
vote
0answers
49 views

Feature maps for a Convolutional Neural Network

I hope this is the right place to ask this, so here goes: I am currently trying to implement a convolutional neural network in C++, but since I have no formal education in signal processing, image ...
1
vote
0answers
50 views

Pearson correlation of neural responses with it's linear estimation

I am trying to understand the following fact from this article (page 13): How can single neurons predict behaviour Suppose I have a linear estimation of a stimulus: $ \hat{s} = \mathbf{w}^T(\mathbf{r}...
1
vote
1answer
878 views

FPGA vs DSP for MAC operations

I'm new to SP Stack Exchange . I am doing a project on implementing a handwriting recognition machine using Neural Networks in Real Time . The Image Processing Part involves convolving a 4*5 kernel ...
1
vote
1answer
179 views

Techniques to reject noisy neural network input

Suppose an artificial neural network is used to approximate a sine wave (shown in red in the graph below), given the linear input variable $x$ (scaled such that the ANN input is $x_{\rm nn}\in[-1;1]$)....
0
votes
1answer
2k views

Is there a penis detection demo similar to face detection?

Tutorial for face detection: Is there a script / tutorial / demo for penis detection? These guys ran into some issues: Fairly serious question, future of internet memes is at stake. Breast / ...
0
votes
2answers
556 views

Neural Network: Spectrogram Dimension

I like to work with a convolutional neural network in combination with a spectrogram as input. Assuming the spectrogram has the dimensions $T\times F$ (time$\times$frequency). Is it more natural to ...
0
votes
1answer
48 views

Deep learning model for phone recognition - issues with dimension the model

I seem to have some problems understandind how the model described in this paper has been designed This is what is written about the model dimension.. ...In these experiments we used one ...
0
votes
1answer
16 views

Training a NN classifier on a single\double channel out of a surround sound dataset

I want to train a neural network for a classification task on the VSD2014 dataset. I have downloaded the movies, but they have a 6 channel audio format (surround sound). 6 channels will cost a very ...
0
votes
1answer
136 views

How to train and test deep neural network using MFCC features?

I am working on Voice Disorder Detection problem. I have extracted 13 MFCC features, 13 delta and 13 delta-delta features from each audio file (2 to 4 secs). I extracted these features for each frame (...
0
votes
1answer
54 views

What does it mean for a Wavelet transform to commute with translations?

Referencing this article here https://arxiv.org/pdf/1203.1513.pdf It states "A wavelet transform commutes with translations, and is therefore not translation invariant". Now I understand why it is a ...
0
votes
1answer
98 views

Neural Network learning project based on 8 wave signals over 1 second at 1 sample every 10 ms ( hence 100Hz )

I'm currentely trying to train a neural network that can decide wether a pattern produced by the movement of a hand near capacitive sensors is as expected, or random. I have an MPR121 microchip linked ...
0
votes
1answer
58 views

Generalizing the chain rule

Given the real-valued functions $f_1$ and $f_2$ with $x\in\mathbb{R}$, then $$ \frac{df_2(f_1(x))}{dx} = \frac{df_2(f_1(x))}{d f_1(x)}\frac{df_1(x)}{dx}$$ Is it then the case that if we also have a ...
0
votes
1answer
220 views

How to apply neural network parallelly on each part of image

I have an image which is divided into four equal size square blocks. I want to apply neural network for denoising. Usually, I apply on the whole image. But i was thinking that is it possible to divide ...
0
votes
1answer
85 views

Answering Machine vs. Human — Neural Network Features Selection

I've been tasked with creating an artificial neural network that can classify a telephone call as either answered by a human or an answering machine. My knowledge of audio processing is, mildly put, ...
0
votes
1answer
179 views

Artificial Neural Network Preprocessing in Real-Time Applications

I've come across an issue with my ANN when attempting to port my offline analysis to an online, real-time, application. I currently train my algorithm using an array of input data, number of ...
0
votes
3answers
749 views

Neural network with much less positive examples

I am developing a medical algorithm working on large amounts of data. However, as in many medical scenarios I have a lot of negative example and only a few positive ones. So any neural network I train ...
0
votes
1answer
73 views

Using STFT as an input to a Neural Net

I'm trying to use the STFT as an input to a neural network. After flattening, there are over 4,000 features for a few seconds of audio. Is there a recommended way of summarising these to be a more ...
0
votes
0answers
15 views

Feature Based Methods for Quality Inspection Problem

I am currently working on an image classification problem to classify thermal images (can be interpreted as false-color images) of certain products as with or without defect. From an initial search in ...
0
votes
0answers
30 views

Filter Bank and Auto-Encoder

I'm trying to find an intuition behind auto-encoder using an analogy with filter banks. I can comprehend the encoder and analysis filters in a filter bank as extracting features from the input signal ...
0
votes
0answers
35 views

How can I find the delay between two signals? [duplicate]

I am using NARX in Matlab. Is there any method to find the delay between input and output signals? My aim is to decrease memory length by finding the delay. TIA.
0
votes
0answers
20 views

How can a CNN account for spectro-temporal constraints in neural data?

What are there the best ways to leverage the unique "geometrical" constraints of spectro-temporal signal representations (architecture, filter shapes, data augmentation, etc.)? For example, ...
0
votes
0answers
15 views

Functioning of a continuous data stream processing neural network?

I've been searching with unfortunately no relevant results about something I have trouble to figure out: neural networks which process continuous data stream (audio, video, anything with a state ...
0
votes
1answer
121 views

STFT to spectrogram

I would like to know whether I am correct in my understanding of going from STFT to a spectrogram. My goal is to convert a spectrogram back to a wav file. If I have my STFT: ...