Human identification using gait analysis

I am working on a human identification by gait analysis project. So far, I have managed to extract the Gait Energy Image(GEI) of a silhouette. I am stuck on finding a way to move forward with my project. I am thinking about applying PCA on the GEI of each silhouette and then using kNN with…

Outliers detection problem in neural networks

Assuming we have big m x n input dataset with m x 1 output vector. It’s a classification problem with only two possible values: either 1 or 0. Now the problem is that almost all elements of the output vector are 0s with a very few 1s (i.e. it’s a sparse vector), such that if…

What is a working configuration of a neuronal network (number of layers, lerning rate and so on) for a specific dataset?

I try to solve some easy functions with a neuronal network (aforge-lib): This is how I generate the dataset: const int GesamtAnzahl = 200; float[,] tempData = new float[GesamtAnzahl, 2]; float minX = float.MaxValue; float maxX = float.MinValue; Random rnd = new Random(); var granzen = new List<int>() { rnd.Next(1, GesamtAnzahl-1), rnd.Next(1, GesamtAnzahl-1), rnd.Next(1, GesamtAnzahl-1),…

How does the forget layer of an LSTM work?

Can someone explain the mathematical intuition behind the forget layer of an LSTM? So as far as I understand it the cell state is essentially long term memory embedding, correct me if I’m wrong, but I’m also assuming it’s a matrix. Then the forget vector is calculated by concatenating the previous hidden state and the…

Automated Annotation of Objects

Given thousands of images, where some of the images contain target objects and others do not, is there an easy way of drawing bounding boxes on these target objects rather than relying on manual annotation? Wouldn’t drawing 4 orientations of an object and their respective bounding boxes and randomly inserting them into the images be…

What is the difference between linear and non-linear regression?

In machine learning, I understand that Linear regression assumes that parameters or weights in equation should be linear. For Example: Y = W1*X1+W2*X2 is a linear equation where X1, X2 are feature variables and W1, W2 are parameters. also, Y = W1*(X1)^2 + W2*(X2)^2 is also linear as parameters (W1, W2) are linear with respect…

CycleGAN for paired data

I am very interested in the application of CycleGANs. I understand the concept of unpaired data and it makes sense to me. But now a question comes to my mind: what if I have enough paired image data, is then a CycleGAN an over-engineering, if I use it in a “supervised” setting (input matches with…

What is the input for the prior model of VQ-VAE?

I’m trying to implement the VQ-VAE model. In there, a continuous variable $x$ is encoded in an array $z$ of discrete latent variables $z_i$ that are mapped each to an embedding vector $e_i$. These vectors can be used to generate an $\hat{x}$ that approximates $x$. In order to obtain a reasonable generative model $p_\theta(x)=\int p_\theta(x|z)p(z)$,…

Why does the denoising autoencoder always returns the same output?

I am trying to implement a denoising autoencoder (DAE) to remove noise from 1024-point FFT spectra. I am using two types of spectra: (1) that contain a distinctive high amplitude spectral peak and (2) that contain only noise peaks. If I understood correctly, I can train the DAE using the corruputed spectra (spectra+noise) and afterwards…

Elastic Weight Consolidation (EWC, fisher’s matrix)

I’m trying to re-implement Elastic Weight Consolidation (EWC) as outlined in this paper? As a reference, I am also using this repo (another implementation). My model/idea is pretty straightforward. Train the network to do the bit operation AND (e.g 1 && 0 = 0) then using EWC, train it to use OR (e.g 1 ||…