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

learn more… | top users | synonyms (1)

0
votes
0answers
19 views

R C5.0 tree model to list conversion

I am using the C5.0 decision tree in R from the C50 package. The training function C5.0 returns a list which also contains a "tree" element which is basically a text representation of the tree. I am ...
0
votes
0answers
43 views

omit variable to find feature importance in classification

I have not seen the following idea about measuring feature importance in classification discussed. Fit model with all variables; get full model classification accuracy Successively fit the model ...
0
votes
0answers
31 views

Decision Theory

Patient X is worried that he may have disease Y. He goes to a doctor who performs some test and based on the test determines that the probability that X has disease Y is 0.3. The insurance company has ...
3
votes
1answer
52 views

Clarification about no free lunch theorem

So I initially thought that the NFL theorem meant that an algorithm that is good at learning in one problem domain is necessarily bad at learning in a different problem domain. But, after reading a ...
3
votes
0answers
31 views

Cut off point with three categories

I have a categorical variable called severity with three categories (low, medium, high) and another numerical variable call ZX that can take values from 0 to 10. I want to find the cut off points of ...
1
vote
0answers
20 views

Is the Laplace/Lidstone smoothing parameter (talking about Multinomial/Bernoulli Naive Bayes) related to the particular structure of the dataset?

I'm working with Multinomial and Bernoulli Naive Bayes implementation of scikit-learn (python) for text classification. I'm using the 20_newsgroups dataset. From the scikit documentation we have: ...
1
vote
1answer
40 views

Neural networks with complex weights

I am currently wishing to give a neural network starting weights with complex values (because of the nature of the specific task I am working with). I was trying to use the standard neural net ...
0
votes
1answer
33 views

Is feature complementarity different from feature interaction?

I am writing a conference paper in which I have a sentence like "...complementary/interactive features...". This sentence ...
1
vote
0answers
20 views

What happens when we feed a 2D matrix to a LSTM layer

Suppose I am feeding a 2D matrix of shape (99,13) as input to a LSTM layer. I am having n number of files, where each contains (99,13) size vectors. I have decided to consider 13 as the number of ...
1
vote
1answer
57 views

When to use regression trees/forests?

As I was looking for a fine regression algorithm for my problem. I found out one can do that with simple decision trees as well, which is usually used for classification. The output would be something ...
1
vote
1answer
24 views

RBF: Linear and non linear cases

I had a course in machine learning but I still have some questions about the RBF (Radial Basis Functions): What is the difference between RBF in linear and non linear cases? How does the RBF work in ...
0
votes
1answer
56 views

How to implement a LSTM based classifier to classify speech files using Keras? [closed]

I am trying to implement a LSTM based classifier to recognize speech. I have a dataset of speech samples which contain spoken utterences of numbers from 0 to 9. Each file contains only one number. I ...
0
votes
0answers
25 views

Out of Sample Cross Validation - Accuracy and Confusion Results

I have a scenario where I validate a trained model on an out of sample set - such that I begin by splitting the entire data set to train/test set. X_train, y_train, X_test, y_test. Then use ...
0
votes
0answers
29 views

Why is the “training score” I get from the learning curve of Multinomial Naive Bayes so different from the training score of the Bernoulli version?

I'm comparing the learning curves of Bernoulli and Multinomial Naive Bayes using the 20_newsgroups dataset from scikit-learn for text-classification. I considered both the "training score" and the ...
0
votes
0answers
13 views

Predict pairwise identity matches between elements

I want to build a model to predict identity matches between elements. My data is as follows: the predictors (X) are some bag of words representation or other ...
0
votes
1answer
38 views

neural networks - What is meant by “linear combination of inputs”

Just starting out with MLPs. I am reading a tutorial that I found here. It says that the disadvantages of using a linear function is that the neural net will only be restricted to learning "linear ...
0
votes
1answer
21 views

Neural Networks - Do all neurons in hidden layer activate?

Noob question. Okay I am beginning with MLPs and machine learning. Suppose that I have 2 hidden layers in an ANN that uses the sigmoid function. So does that mean that after calculating the ...
1
vote
2answers
55 views

What does “the process that generates the data” mean? and How does feature selection help in recovering it?

In [1], one of the motivations to use feature selection is stated to be: "to gain knowledge about the process that generated the data". What does this "process" actually mean? and How does feature ...
1
vote
0answers
26 views

SVM - non separable case/soft margin, where are the support vectors

My Question is - in the inseparable case(where we add slack variables) $\begin{equation*} \begin{aligned} & \underset{w}{\text{minimize}} & & \ ||w||^2 + C \sum_{1}^{m} \epsilon_i\\ ...
1
vote
1answer
68 views

Predicting with Restricted Boltzmann Machines for Collaborative Filtering

Restricted Boltzmann Machines (RBMs) were used in the Netflix competition to improve the prediction of user ratings for movies based on collaborative filtering. I think I understand how to use RBMs ...
2
votes
0answers
64 views

Why does discriminant analysis prevent us from finding more than $K-1$ linear 'features' and what does it mean?

According to Bishop's Machine Learning and Pattern Recognition, the cost function for linear discriminant analysis (LDA) with $K>2$ classes is $$J(\mathbf w) = \mathrm{Tr}\left\{\left(\mathbf W ...
1
vote
1answer
72 views

how to handle small datasets with large dimensions

I have 48 samples which are case and control and 27000 features for each sample so my matrix is [48 X 27000]and I am using Deep belief networks(DBN) as my algorithm to predict the accuracy of the ...
0
votes
0answers
18 views

Recommended Reading - Covariance & Correlation in R for Time Series [duplicate]

I'm at the beginnings of trying to find this out, and much of the reading out there is not quite what I'm looking for. I'm looking for recommended reading for determining correlation or covariance ...
0
votes
0answers
9 views

Can neural nets/genetic algorithms be used to interpret EEG data?

Research into brain-computer interface is big business, in particular for the medical applications, not to mention probably every industry that deals with computer systems. EEG hardware seems to be ...
0
votes
0answers
12 views

rolling window for time series- permutation issue

Suppose that I am interested in a one step-ahead prediction of the value of some time series, and I want to use, let's say, a Support Vector Machine to do the task. A very common way to set up the ...
0
votes
0answers
27 views

R - Plotting a ROC curve for a Naive Bayes classifier using ROCR. Not sure if I'm plotting it correctly

I have a Naive Bayes classifiers that I'm using to try to predict whether a game is going to win or lose based on historical data. The model has 25 variables in total, all of which are categorical ...
3
votes
1answer
56 views

Input Normalisation for ReLU neurons

According to LeCun (1998) it is good practice to normalise all inputs so that they are centred around 0 and lie within the range of the maximum second derivative. So for example we would use ...
0
votes
0answers
17 views

Apply PCA on classification data, category wise or on complete dataset?

I have a classification related image data with 15 different classes and each class has five feature sets. Those five feature sets comprise of colour features, sift features etc.. upto 5 different ...
0
votes
0answers
16 views

Perceptron Inseparable Case - Hinge loss

I am trying to understand the case where the perceptron algorithm can't find a perfect seperator. I am trying to understand how we bound the number of mistakes by using the hinge loss. My intuition ...
1
vote
0answers
23 views

Why is optimal learning rate obtained from analyzing gradient descent algorithm rarely (never) used in practice?

Why is optimal learning rate obtained from analyzing gradient descent algorithm rarely (never) used in practice? Gradient descent procedure is to iteratively do $a(k+1) = a(k) - \eta(k)\nabla ...
6
votes
1answer
259 views

Are there applications where SVM is still superior?

SVM algorithm is quite old - it was developed 1960s, but was extremely popular in 1990s and 2000s. It is a classical (and quite beautiful) part of machine learning courses. Today it seems that in ...
1
vote
0answers
24 views

Which standard deviation of the cross-validation score?

When doing cross-validation for model selection, I found there are many ways to quote the "standard deviation" for the cross-validation scores (here "score" means an evaluation metric e.g. accuracy, ...
1
vote
0answers
20 views

Practicality of sparse inverse covariance matrix assumptions

For a set of $p$ datapoints in $m$ dimensional space, if the features are packed in a $p\times m$ matrix $X$, then $C = XX^T$ is the covariance matrix and $K = C^{-1}$ is the inverse covariance ...
0
votes
0answers
8 views

Gbm fit on unbalanced sample

I'm trying to build a model using GBM in r in order to get probability of two classes ( 'yes','no'). My data are unbalanced, and because of this I trained my model using a balanced data(undersampling ...
1
vote
2answers
76 views

Calculating F-Score, which is the “positive” class, the majority or minority class?

I'm calculating the F-Score for a sandbox dataset: 100 medical patients, 20 of which have cancer. Our classifier mis-classifies 20 healthy patients as having cancer, and 5 patients with cancer as ...
0
votes
0answers
20 views

Why SVR kernels other than 'linear' don't work for this toy dataset!

I'm a little new with modeling techniques and I'm trying to compare SVR and Linear Regression. I've used f(x) = 5x+10 linear function to generate training and test data set. Here we've discussed why ...
3
votes
0answers
324 views

Dealing with auxiliary random variables for Mean-Field Variational Inference in Bayesian Poisson factorization

I am studying as a part of a class assignment a recent paper on Poisson factorization. Some points of the paper regarding the usage of some auxiliary variables are not clear to me. I would like to ...
0
votes
0answers
21 views

What techniques I should look to predict next user behavior in a series?

I have a dataset, when users repeat an action (let's say, to choose a value between 1 and 10) many times (let's say 10 times). I want to predict the behavior of users at the 10th action, based on his ...
1
vote
2answers
37 views

R - glasso very slow for high feature space

all, I'm doing a graphical lasso in order to approximate the inverse of the covariance matrix of a 1200 (p-features) by 100 or so (n observations) data matrix. Basically, I'm inverting a 1200 x 1200 ...
0
votes
0answers
15 views

L2 Regularization and Penalized Splines

I am fairly new to the concept of L2 Regularization - does something like "penalized splines" qualify as this?
0
votes
0answers
32 views

Mercer's condition

I am having a very hard time understanding Mercer kernel. If any sequence of data points $x_1, ... , x_n \in R^d$ and coefficients $c_1, ... , c_n \in R$, satisifies the inequality $\sum^n_{i=1} ...
3
votes
1answer
147 views

Understanding probabilistic neural networks

I would like to understand the basic concepts of probabilistic neural networks better. Unfortunately so far I have not found a resource which answers all the questions I have. So far my understanding ...
20
votes
4answers
3k views

What is the name of this chart showing false and true positive rates and how is it generated?

The image below shows a continuous curve of false positive rates vs. true positive rates: However, what I don't immediately get is how these rates are being calculated. If a method is applied to a ...
0
votes
1answer
38 views

What is the use of distance matrix in clustering algorithms?

I found a C library for clustering and I was reading about the distance matrix here: it says: The first step in clustering problems is usually to calculate the distance matrix. This matrix ...
1
vote
1answer
57 views

In word2vec, for analogies do we use “in” or “out” vectors?

In word2vec each word is associated with two vectors (one for in and one for out) so that it predicts conditional probability: $$P(word_{out}|word_{in}) = \frac{\exp(v_{in} \cdot ...
0
votes
0answers
14 views

Is it acceptable to use class probabilities as weights for a weighted average when the bins are numbers 1 to 5?

I have a Multi Class SVM that can predict what class some observation belongs to. There are 5 classes. They are trained for observation that scored 1 to 5. I want the MC-SVM to predict a class for ...
0
votes
1answer
27 views

Split dataset by categorical variable or use as a dummy/factor variable?

I'm looking for any sort of best practice or ways to go about this situation. Often I come across datasets that have a categorical variable that I am tempted to split off the main dataset into ...
0
votes
0answers
22 views

Sparse coding - Machine learning and spectral clustering

I am just trying to understand what does this term mean. I am not able to find nice explanation. The sparse code is when each item is encoded by the strong activation of a relatively small set ...
3
votes
1answer
43 views

Optimizing Neural Network speed for larger inputs (Facial Recognition)

I am building a neural network to recognise the difference between male and female. The issue is that I have a database with a collection of 250x250 pixels (Not x 3 since I convert to grey-scale). ...
-1
votes
2answers
23 views

How to find similar kind of project specification using Clustering Algorithm?

I have budget estimation of some bio-medical projects and their specification details. Could any one suggest me how to do clustering algorithm to find the similar kind of specification. Which ...