Methods and principles of building "computer systems that automatically improve with experience."

learn more… | top users | synonyms (1)

0
votes
1answer
24 views

Difference between neural network architectures

Can someone explain to me the differences between the following neural network network architectures? How are they different in their prediction settings? Which networks are still used today, and why? ...
0
votes
0answers
9 views

SKLearn SVC predicting perfectly with random features

I am using an SVC to do binary classification. I am using the rbf kernel and doing leave-one-out cross validation to choose my value of C. I ran the model using my normal features and had a detection ...
0
votes
0answers
4 views

How to design a testing rule to fastest differentiate skilled from unskilled experts?

The problem is as follows. There are $n$ securities. In each period $t$, a random return vector $R_t = \alpha_t + \epsilon_t$ will be drawn, where $\alpha_t \sim N(0,\Sigma_\alpha)$ and $\epsilon_t ...
2
votes
0answers
9 views

Are there any open-source implementations of structured prediction methods? [on hold]

I'm currently interested in structured prediction field. I've looked around the web but haven't found any implementations of this kind of algorithms in any of languages. Have I not searched enough or ...
0
votes
0answers
27 views

Find best K value for K-Means clustering [on hold]

I'm doing the K-Means clustering for my data. Following python script does K-Means for 2 clusters. ...
3
votes
1answer
20 views

Duplicate Training Data in Decision Tree Learning Algortihm

I have the following training data set where the first line shows the name of attributes. ...
0
votes
0answers
15 views

Rules for choosing how much training data one needs to learn a Radial Basis Function model?

I was trying to understand how much data I would need compared to the number of parameters (and to have good generalization) when I train a radial basis function (RBF) network on a regression task ...
0
votes
1answer
4 views

State-of-the-art sampling methods for different information about target density

I was wondering what are the current state-of-the-art methods (aka your favourite methods, if you are an expert) for Monte Carlo sampling from a target density function $f(x)$ with $x \in ...
0
votes
0answers
13 views

How you free up memory or handle it while fitting/cross-validating model in Scikitlearn? [on hold]

I am trying to fit my model using regression trees but the problem is, it consumes a lot of RAM, which makes my code unresponsive. By looking at different forums and platforms, I think this is a ...
3
votes
1answer
26 views

how to use sparse Dirichlet prior in Dirichlet-Multinomial models?

Consider a Dirichlet-Multinomial model, with a (symmetric) Dirichlet prior on a probability distribution $\theta$, where: $\theta \sim Dir(\alpha_1,...,\alpha_K)$ and $X \sim Mult(\theta)$. When we ...
0
votes
0answers
18 views

Measuring the performance of a binary classifier

I've build a binary classifier (text classification for spam non spam emails) based on DT classifier using scikit learn and I am training the classifier and testing different test sets 'sorted ...
0
votes
0answers
11 views

Analysis of classification result

Assume you observed a system for 24 hours and collected data points each minute (each data points contain some host information like cpu_usage,... All elements are numeric). Also, there is a trained ...
0
votes
0answers
14 views

How to transform the LDA model to see the topic evolution in chat content?

Now I have a data set with about 13,000 lines, including the date, sender, chat content in a public server. The data set covers about ...
1
vote
0answers
7 views

Multiple time series - class of problem with agents and events?

I'm working on a prediction problem and struggling to find applicable resources (articles, tutorials, papers) that address this class of problem. I'm assuming the info is out there and I'd love to ...
0
votes
0answers
22 views

Comparing classification accuracies with different numbers of features

I have a classification problem in which I’m trying to assign a label to each of a collection of inputs x_i. I’m comparing two different feature representations of the inputs, trying to determine ...
0
votes
0answers
9 views

How to generate n theano.shared variables for Gaussian mixture regression?

I am trying to program a Gaussian mixture regression using python, and the theano package. Suppose I have n clusters, then I need to generate n regression weight matrices for each cluster (also, n ...
1
vote
0answers
24 views

Can I be confident of my R^2 score?

I have a dataset with 10 variables and 158 observations. I used cross-validation, grid-search and ElasticNet algorithm. To evaluate the model I checked the pearson correlation between the 10 ...
0
votes
1answer
16 views

Predictive Analytics, Rare Outcome, Multiple Regresson [on hold]

I'm looking at a data set with ~50,000 observations, ~800 outcomes of interest, with ~30 dichotomous (yes/no) variables for each observation. My goal is to create a predictive rule that will predict ...
0
votes
0answers
20 views

Face detection in R [on hold]

I'm trying to get started with this area (face detection) and I see a lack of information with R language. Are there any example or algorithm for face detection in ...
1
vote
1answer
22 views

What happens if you square an RBF kernel function?

Let's say we use a kernel regularization algorithm such as ridge regression to minimize some loss in an RBF kernel: $$\min_{h \in H} \frac{1}{n} \sum_i (h(x_i) - y(x_i))^2 + ||h||^2_K$$ We get some ...
1
vote
0answers
26 views

Improving the results coming from an image recognition API

We are developing a software application that will automatically suggest tags (keywords) for images that are being uploaded into a database of already-tagged (by a human) images. We are using a 3rd ...
3
votes
0answers
18 views

Propagating uncertainties using random forest out-of-bag accuracy estimates

Let's say I train a random forest on some data and get an out-of-bag accuracy estimate of 90%. I then predict a quantity using this trained forest. What should be the uncertainty I give to that ...
0
votes
0answers
24 views

Compare the performance of a classifier on original and under-sampled data set?

I want to evaluate the performance of a classifier with original imbalance data set and after under sampling the data set. Kindly guide me whether my approach is alright or not , if not than how ...
0
votes
0answers
37 views

Classification and convex optimization of the cost function

From the literature I read that For a neural network, the cost function, J(W,b) is a non-convex function, gradient descent is susceptible to local optima; however, in practice gradient descent ...
0
votes
0answers
18 views

Can I create a convolutional neural network with this data?

I have a dataset of 80 CT scan images and want to use a convolutional neural network (conv net) for classification. I was thinking of taking 40 images, augmenting them with 5 degree rotations over 360 ...
0
votes
0answers
30 views

Encog Lunar Lander Extended

This question is with reference to C#'s Lunar Lander Example obtained in Encog repository. As the example suggests, I am using NeuralSimulatedAnnealing to train my multi-layer feedforward network (50 ...
0
votes
0answers
12 views

How to measure accuracy, precision, recall with incomplete information?

Let me give an example. Assuming I have a classification technique for automatically measuring if a part in a car needs repair or not, it is my goal to check my classifier results against the ground ...
0
votes
0answers
6 views

Naive Bayes Bernoulli with more than 2 class labels?

I am a little confused about how to perform Naive Bayes Bernoulli model. In the first link, they split the class labels and the predictors. It is a binary class label here. But what if I do not have a ...
1
vote
0answers
30 views

Cost function: output layer should sum up to roughly 1

I have a convolutional neural network classifying some images for me. The output layer is not one-hot encoded but outputs a distribution around the predicted class (because neighboring classes are ...
0
votes
0answers
28 views

Creating Naive Bayes Model for numerical data in R

I want to calculate the missing value using the NaiveBayes predictor. I am using a dataset with missing values at some rows, ...
3
votes
2answers
92 views

Gradient descent: compute partial derivative of arbitrary cost function by hand or through software?

I'm a software engineer, and I'm working my way through Stanford professor Andrew Ng's online course on machine learning. I'm able to follow most of the math related to gradient descent for linear ...
3
votes
1answer
41 views

Accuracy in neural network for regression

I want to measure the accuracy in neural network that performs regression. I have two outputs. Is the root-mean-square deviation ( RMS wiki) the right way to go? From wikipedia RMSD is a good ...
0
votes
0answers
20 views

Is Deep Neural Networks suitable for Cancer Detection? [on hold]

I am currently working on a project which main topic is to analyze a patient's medical images in order to know if she is affected by Cervical Cancer or not. One image contains 6000 pixels. For each ...
-1
votes
0answers
29 views

Who is most likely to create Artificial General Intellgence first? [on hold]

Is it Jürgen Schmidhuber with his Gödel Machine? If not, please state your reasons
0
votes
0answers
7 views

What is the type of precision in the prior distribution over user's and item's latent factors in PMF?

I am trying to implement the pmf model in stan. paper In this model, there are two prior normal distribution over the latent factors of users and items: $U_i$ ~ $normal(0,\sigma^2I$) And it is said ...
1
vote
1answer
23 views

Categorical with many levels for NN

I have a dataset which lists the amount of seconds a user held a session by browser_type. For example: ...
0
votes
1answer
7 views

Non-biased User Interface for building training set

I want to use machine learning to detect objects of type A among objects of types B-Z. I require human expertise to initially classify these objects as A, B, C... Z. The individuals who can provide ...
0
votes
1answer
22 views

Support Vector Machine: Output simulation from mathematical equations

If I have trained SVM model using the RBF kernel, how do i simulate the SVM output using the trained model and mathematical equations? How do I transform the test data? I am trying to write a code ...
2
votes
1answer
20 views

Learning the joint probability distribution of 3 variables from partial observations

I have a dataset composed of 3 random variables X, Y and Z. However, at each sample one of the random variable remains hidden. As an arbitrary example, the observation 1 is $(x_1,y_1)$, the ...
1
vote
0answers
15 views

Comparing corpuses with different vocabulary?

How can we compare two corpuses with different vocabulary? Basically, we have a bunch of distributions for different vocabularies that we want to compare. But all the vocabularies are different ...
0
votes
0answers
10 views

Almost a multinomial logistic regression

Is there a way to train a multinomial logistic model where the true classification is unknown, but summary information obtained from the true classifications is known? Illustrative Example: 5 ...
0
votes
1answer
19 views

Validation of Support Vector Machine using sklearn

I have made a recording of two different sounds and I want to use an SVM in order to be able to distinct between the two. The process I have followed is: Divided each sound in multiple 20ms frames. ...
0
votes
0answers
8 views

Can you help me to plot the result of support vector machine regression using matlab/libsvm?

Can you help me to find the code that plotting the result of support vector regression using matlab/libsvm using 6 dimension features and 1 predictor variable?
1
vote
0answers
40 views

What is the minimum sample size required to train a Deep Learning model - CNN?

It is true that the sample size depends on the nature of the problem and the architecture implemented. But, on average, what is the typical sample size utilized for training a deep learning framework? ...
5
votes
2answers
63 views

What is energy minimization in machine learning?

I was reading about optimization for an ill-posed problem in computer vision and came across the explanation below about optimization on Wikipedia. What I don't understand is, why do they call this ...
0
votes
0answers
17 views

What is discretization in machine learning? [closed]

Why do we need discretization? which classifier is needed for discretization?
0
votes
2answers
37 views

What it mean by Training SVM

I am new to image processing. As my project I am doing "image classifier using SVM". I have the idea of my final software "I select some image and give it as input to my software and it will classify ...
0
votes
0answers
30 views

What is the Bernoulli class conditional distribution?

What is the Bernoulli class conditional distribution? I am trying to implement a procedure for computing a naive Bayes classifier for binary features with a Bernoulli class conditional distribution. ...
0
votes
0answers
27 views

Using Deep-Learning for Cancer Detection [closed]

I am going to work on a project which main topic is to analyze patients' medical images in order to know whether he is affected by cervical cancer or not. The Machine Learning technique which has to ...
0
votes
0answers
18 views

Which machine learning approach/algorithm do I choose for path validation?

I apologize for lack of terminology, I'm no computer scientist. I have a problem of validating paths in a directed graph with complex nodes. The full description is the following: I have a decent ...