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

learn more… | top users | synonyms

0
votes
0answers
19 views

Learning theory for search data?

Has learning theory ever been applied in practice for search log data? If so, what are some findings about generalization/learnability from this data? I'm interested in generalization about an ...
0
votes
0answers
20 views

Custom Neural network in matlab

I am trying to make a custom Neural network structure using 'network' command. I am a little confused.Can we change the connections between individual neurons?Like it is possible in weka?
0
votes
1answer
23 views

How to get both MSE and R2 from a sklearn GridSearchCV?

I can use a GridSearchCV on a pipeline and specify scoring to either be 'MSE' or 'R2'. I can then access ...
1
vote
1answer
67 views

Support Vector Machine Question

I need help with the following problem. I provided my current (partial) solution, and I hope someone can correct me and/or give me suggestions as to how I should solve the parts that I've left out. ...
0
votes
0answers
40 views

MATLAB interperetation of Neural networks

I am new to Neural networks and I am trying to build a custom neural network using the NN toolbox in MATLAB.I am using the "create custom neural network function". Now, I find the neural network ...
8
votes
3answers
2k views

Why do people like smooth data?

I am to use the Squared Exponential kernel (SE) for Gaussian Process Regression. The advantages of this kernel are: 1) simple: only 3 hyperparameters; 2) smooth: this kernel is Gaussian. Why do ...
2
votes
1answer
104 views

Some questions on Principal Component Analysis (PCA)

I am trying to understand some descriptions about PCA (the first 2 are from Wikipedia): 1) Principal components are guaranteed to be independent only if the data set is jointly normally distributed. ...
0
votes
0answers
17 views

Extraction of a decision boundary (LDA) after a systematic querying of the feature space and convolution with Sobel filter (examples in numpy)

I am doing some experiments with LDA (Linear Discriminant Analysis), in python. Now I am at the point in which I would like to display the separation planes in the 3-dimensional feature space. I ...
0
votes
0answers
8 views

S and N parameters of Ridor

I am using WEKA and in particular their implementation of Ridor. The documentation says this about the parameters S and N: -S Set number of shuffles to randomize the data in order to get better ...
2
votes
1answer
44 views

Differences in AUC calculation between pROC and ROCR

Does anyone know the difference in calculation between these two AUC packages? They get different results when I add in positives with predicted value of 0 (simulating a prob model where many outputs ...
1
vote
0answers
31 views

PCA + L1 equivalent to elastic net?

I am performing a logistic regression on a rather big dataset (700k+ samples and 1k+ features). I suspect that a lot of these features will be highly correlated and multicollinearity can be an issue. ...
6
votes
2answers
152 views

Clustering a noisy data or with outliers

I have a noisy data of two variables like this. ...
1
vote
1answer
108 views

What are basic differences between Kernel Approaches to Unsupervised and Supervised Machine Learning

I got nice graphical representation of Machine learning for clustering / classification. Source: Kernel Approaches to Unsupervised and Supervised Machine Learning by Sun-Yuan Kung Here are my ...
0
votes
0answers
9 views

When to cluster features for supervised learning?

I'm doing a project on dog adoption patterns, and I realized that there are many (100 +) different breeds of dogs. I'd like to build a predictive model using breed as covariate, but I'm not sure ...
3
votes
2answers
99 views

Estimating the time for completing a sequence of actions

In short: suppose I have observations for times taken to do some action. I want to estimate, how long will it take to complete a sequence of actions. The estimate should minimize the mean absolute ...
4
votes
2answers
47 views

When do kernel based method perform better than the regular

I am used with linear models. I can see rising use of kernel based method particularly in machine learning. The following is an example Gaussian kernel using ...
0
votes
0answers
36 views

Neural-Net style pattern recognition with an unknown/varying number of inputs?

Say for example I had a weighted graph such that each node had an associated value. The nodes' values are given by some function of the edge weights and the number of edges as well as the node's ...
1
vote
0answers
24 views

Low pass filter to maintain edge information

I am looking for a kernel as low pass filter that satisfy as:I must find a kernel that statisfies as follows: In the my reference paper, the author suggest gaussian kernel that is The gaussian ...
0
votes
1answer
33 views

kernels and similarity (in R)

I am trying fit different kernels to calculate similarity matrix in R. Here is example data - X matrix : ...
0
votes
1answer
46 views

How to select kernel for Gaussian Process?

In Gaussian Process (GP), the kernel (co-variance function) is used to measure the similarity between one point and a given point. There are so many kernel functions for GP, and I wonder how to select ...
0
votes
2answers
30 views

Dummy Variables and Learning algorithms

Suppose a predictor variable $x$ is nominal/categorical with three levels: $1,2,3$. Thus we create two dummy variables $x_2$ and $x_3$ with level $1$ as the reference variable. Let $y$ be a binary ...
1
vote
0answers
83 views

Machine Learning Process for detecting edges of overlapping objects with OpenCV

I'm quite new to machine learning and a bit unsure about the whole process and the interpretation of the results. The Task: I have images with some objects of somewhat the same color and shape which ...
2
votes
1answer
38 views

full batch v.s. online learning v.s. mini batch

This is a question from a coursera course: Suppose we have a set of examples and Brian comes in and duplicates every example, then randomly reorders the examples. We now have twice as many examples, ...
2
votes
1answer
66 views

Predict observation using Hidden Markov Models

I have a sequence of observations e.g. ["Click","Scroll","Hover","Zoom","Select"]. I need to predict the next value of this observation sequence but not the next hidden state. I know that there are ...
0
votes
0answers
9 views

Represents istances with multiple values for an attribute and similarity between them

In the scenario in which I'm working each entity could be represented in terms of ten distinct properties that I will call p1, p2, ..., pn. For each of them, an entity, can have its specific range of ...
0
votes
0answers
25 views

Minimizing the Training data

I have a grey-box model of the form Y= a + b X1 + c X2. Where a, b and c are the coefficients based on regression. The regression variables X1 and X2 are determined based on ...
0
votes
0answers
5 views

Design a feature with time and presence information

Context: I am working on a decision tree classifier, trying to classify businesses as to whether they are likely to have an event occur (default) in the next 90 days. One input I get is whether, and ...
0
votes
1answer
30 views

Conceptual question on optimization

What is the intuition and the physical meaning of the mathematical expression in convex optimization? When using optimization algorithms like particle swarm or genetic algorithm, do they have ...
4
votes
1answer
527 views

What is being learnt?

This may seem a trivial question but I have a fundamental problem in understanding learning. In supervised learning, given and input-output pair, what are we learning? Are we learning the inputs ...
0
votes
0answers
44 views

Profile variable in collaborative filtering

I'm trying to create a recommendation system based on purchases. I did some tests and I found that for some groups of customers, the recommender works very well, but not for others. How can I ...
1
vote
1answer
43 views

Difference between estimation and learning

What is the difference between parameter estimation which includes system identification and learning in machine learning perspective? Let say the model is y= Ax. x is the input and y is the output. ...
0
votes
0answers
8 views

Categorizing text into IPTC subjects

Does anyone know where I can find a corpus I can use to train a classifier into IPTC news categories (http://www.iptc.org/site/NewsCodes/) ? A google search was not very useful. Thank you
0
votes
0answers
21 views

The variance-covariance matrix of the least squares parameter estimatimation

I'm learning Linear Regression for Regression from "The Elements of Statistical Learning". Why The variance-covariance matrix of the least squares parameter estimates is easily derived( from(3.6) ...
0
votes
0answers
31 views

Anomaly detection of web browsing sequences

Please consider that I'm quite new to machine learning. I need to create models based on browsing patterns of web users and find deviations from that model. I'm using web server access log files. For ...
2
votes
0answers
46 views

Basic idea of zero inflated two part models(hurdel) and application to big data (machine learning)

I'm currently working on the data which has 90% 0s in response variable. Based on my research, it seems zero inflated models could be a solution to this. However, while I was reading related ...
0
votes
0answers
11 views

Comparing learning algorithms

I know that you can compare learning algorithms based on their average cross-validation accuracy (e.g 10-fold, 10-repeated CV) and their test set accuracy. Suppose model 1 is a logistic regression ...
0
votes
0answers
40 views

Algorithm for online handwriting recognition

Is there any specific algorithm for online handwriting recognition? The algorithm should recognize non-cursive and cursive handwriting. I know there is already a similar post on stackoverflow.com, ...
1
vote
0answers
27 views

How to understand kernel functions and how to choose a suitable kernel?

I am trying to describe my understand of kernels in the Support Vector Machine(SVM) and why some of them are more popular, but I am not sure if I misunderstand these concepts: 1) There are a large ...
1
vote
1answer
29 views

MDP value iteration

In Markov decision processes, what is the guarantee that value iteration chooses the same policy action from a given state for every iteration? I am referring to the slides given by AWM at ...
0
votes
0answers
21 views

Statistical Methods for Calculating Vending Machine Refill

Am looking into statics to help support a project I am undertaking. The project scope concerns intelligent replenishment / refill of vending machines. During an onsite service, a technician must ...
2
votes
2answers
119 views

ROC vs. Accuracy [duplicate]

If you want to compare two learning algorithms, which metric is better to use in general: ROC or accuracy? I understand that in ROC, you get both the sensitivity and specificity?
1
vote
0answers
15 views

Abnormalities in results L-LDA

For my research I am using Labelled Latent Dirichlet Allocation (L-LDA) on Reuters-21578 ModApte split dataset. In this dataset the news stories have a title and a body. To test the effect of L-LDA, I ...
0
votes
1answer
38 views

How do you measure the accuracy of an inference hypothesis/procedure?

Take inference to mean reasoning/predicting the value of a hidden/laten variable $Z$ given some evidence/data $X$. For example, maybe you are trying to find out if your patient has Cancer (Z = 1 if he ...
0
votes
1answer
18 views

How to apply properly k-nn algorithm when having several attributes

Let assume I have a dataset like this dataset where there are several textual attributes even continuos attributes like age. I have always encountered cases where k-nn is applied on just two ...
3
votes
2answers
130 views

About cross-validation for machine learning

Assume I have 1000 samples of data. I split the data randomly into training and test sets of size 800 and 200, respectively. Now, I train a classifier using the training set, and then evaluate the ...
1
vote
1answer
76 views

Does the vanishing gradient in RNNs present a problem?

One of the often cited issues in RNN training is the vanishing gradient problem [1,2,3,4]. However, I came across several papers by Anton Maximilian Schaefer, Steffen Udluft and Hans-Georg Zimmermann ...
0
votes
0answers
17 views

Propensity in linear models and bilinear regression models

I'm reading this paper about matrix factorization. In the paper they want to combine the features of the nodes in the model (page 6). First they illustrate the simple idea of combining the features of ...
0
votes
0answers
18 views

Intuition behind matrix factorization formulations?

I'm reading this paper about matrix factorization. In the paper they propose to use this factorization for the adjacency (or similarity) matrix $G$ using the following formulation: $G = U \Lambda U^T$ ...
3
votes
2answers
65 views

Assigning even partitions for Cross-Validation

This is a very basic question about cross-validation. Say that I have a sample size of 2901(or any difficult to divide number). How do I split this up into equal partitions (other than n=1)? And how ...
2
votes
1answer
36 views

One-class Classification of multidimensional vectors

I have a m x k User-feature matrix (m >> k) obtained by factorizing an original User-websites matrix (m x n) that has #page views as entries. Additionally, there are users (say r) who have been ...