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

learn more… | top users | synonyms (1)

0
votes
0answers
10 views

Model selection and performance evaluation using cross-validation for time series with missing values

So my task is to select and evaluate a statistical model (random forest, boosted trees, neural networks etc.) for a time series with missing values around 10 years long. One of the goals of that is to ...
0
votes
0answers
6 views

Obtain Precision and Recall from Click through data

I am trying to build a graph of precision and recall using click data. I have two data sources. First data source has all the user clicked item_ids based on a given query_id. Second data source has ...
0
votes
0answers
5 views

Creating a model for a webshop

I'm going to create a Multi-armed bandit algorithm to handle recommendations for a large scale webshop. I'm going to use Thompson sampling (http://en.wikipedia.org/wiki/Thompson_sampling) and would ...
0
votes
1answer
26 views

Why can we assume that samples $X_i$'s are independent if the parameter is fixed (though unknown)?

To put it in context, I was trying to learn Bayesian parameter estimation (by an example of learning the probability of heads of a coin) and was trying to understand the independence of the samples ...
0
votes
1answer
26 views

What gradient descent method is better for convolutional neural network?

Let's say we want to train a convolutional neural network, what gradient descent method works better? (1) Batch gradient descend (2) stochastic gradient descent
0
votes
0answers
11 views

What are the difference between independent space analysis and independent component analysis?

What are the difference between independent space analysis(ISA) and independent component analysis(ICA)?
2
votes
2answers
66 views

Bayesian Linear Regression

I have the following question concerning Bayesian linear regression on my machine learning assignment: Consider $f = w^Tx$, where $p(w) ∼ N(w | 0, Σ)$. Show that $p(f | x)$ is Gaussian. I ...
0
votes
0answers
9 views

Formulating a classification problem as a Hidden Markov Model problem

I am told that this is a better place to ask for help on formulating a Hidden Markov Model: I am given a series of lines coming in one at a time. Each line contains 100 elements (basically gray scale ...
0
votes
0answers
3 views

What does ROC-EER in percent stand for?

Ive tried to understand what the ROC Curve represents and what EER (Equal Error Rate) means. And I somehow think I got to understand some of the explanations I read on the internet and videos I ...
1
vote
0answers
16 views

What is weakly-labeled data?

I am afraid I ask an easy question, but here are my questions: What is weakly-labeled data and is there any strongly-labeled data? In what situation do we use them?
0
votes
1answer
27 views

Time series with multiple subjects and multiple variables in R

I'm having trouble finding a time series technique to deal with a data set I am working on. It contains multiple subjects and multiple variables, not all of which will likely be part of the time ...
0
votes
0answers
8 views

SIFT rotation invariance

In Scale-Invariant Feature Transform, keypoints in an image are extracted which are invariant to scale, rotation and translation. The keypoints contain information on the scale and gradient of a given ...
1
vote
0answers
19 views

Observed versus hidden variables for Bayesian network in this particular context

I am a novice in Bayesian networks. I have a problem which is best described (at least I think so) in the following story. One wants to predict earthquakes. Let's say it has 5 variables, the last one ...
-1
votes
0answers
35 views

When to use K mean clustering and hierarchical clustering algorithm? [on hold]

Can you please tell me when to use the K-mean clustering and hierarchical clustering algorithm and what is the different between them... Regards, Rahul
3
votes
3answers
76 views

Explanation on a Minsky's critique on statistical learning related to XOR

I was listening to the first session of society of Minds by Minsky (2011) and he mentions at some point around minute 48 the following: "...lots of statistical learning tools is good for lots of ...
0
votes
2answers
20 views

Inferring on an unknown number of function approximation

I want to ask whether a procedure to do the following job exists (or whether it makes sense for it to exist). First, assume we have $k$ functions $f_1,...f_k$ that have the same domain and range. ...
0
votes
0answers
26 views

Find distribution of Bus arrival time

I am currently working on a problem in my research which can be modeled into the following question: Let's say I have a rich dataset with values for the variable $A$ which is equal to ...
1
vote
0answers
10 views

Machine learning/random forests with noisy response data

Machine learning techniques like random forests seem to assume that the responses in the training set are known perfectly. Specifically for regression applications, it seems one needs to account for ...
0
votes
0answers
8 views

Viability of software dev - Use of and requirements of NN

Hello I would like to know this two things regarding the viability of producting a software, so: 1) Are available on internet some OCR libraries for free? Can I train my own NN having only a laptop? ...
0
votes
1answer
23 views

What is a good model for revenue managment / price optimization problem

I am trying to create a dynamic pricing model to optimize revenue for a hypothetical business. Lets say I have an application that connects dog walkers to people who want to pay for their dog to get ...
0
votes
1answer
26 views

make prediction with HMM

I want to use HMM to make some prediction. say $O$ is the observation, $S$ is the hidden states, and I know how to train the model with forward-backward algorithm. I just get confused with how to ...
2
votes
1answer
49 views

K-means clustering feature selection

I have a set of English and foreign language documents that I would to perform k-means clustering on to find document groups by topic. These documents are concatenated social media comments for ...
2
votes
1answer
41 views

One model performs better than the other. How to measure if it is statistically significant?

So, let's say that I train two models on the same dataset. I run the experiment once and I get the following results: Using a Neural Network I get an AUC ROC of 0.941. Using Random Forest I get an ...
-1
votes
2answers
36 views

What is the difference between a neural network and a perceptron?

Is there any difference between the terms "neural network" and "perceptron"?
8
votes
1answer
63 views

Are there any contemporary uses of jackknifing?

The question: Bootstrapping is superior to jackknifing; however, I am wondering if there are instances where jackknifing is the only or at least a viable option for characterizing uncertainty from ...
0
votes
0answers
8 views

svmlight for unbalanced data [closed]

I'm using svmlight for multiclass classification using one vs rest strategy. I'm having highly unbalanced data. One data set has 5000 and other set has 500.How to train this unbalanced data in ...
3
votes
1answer
55 views

What does the k-value stand for in a KNN model?

What is the k-value in a KNN classification model? Is K the number of Clusters?
0
votes
0answers
30 views

What are the potential disadvantages of doing kernel PCA?

I was trying to learn more of the motivation around kernel PCA. Its clear to me that one might need to change the representation of the data if it lies in a non-linear space, hence, the projection ...
0
votes
0answers
9 views

Bayesian network overfit - number of features and examples

For a dataset consisting of 150 examples (mostly binary features) what would be the number of features needed so that a Bayesian network doesn't overfit? I know there is no exact answer and I've ...
0
votes
1answer
24 views

Is there AUC for neural network?

I am confused about how to calculate AUC for neural network with a softmax classifier. For example, I know that for SVM, we can change the threshold value and determine the AUC. WHat about in neural ...
0
votes
0answers
8 views

Number of parameters in multinomial logistic regression

In Chapter 10 (Directed graphical models) of Murphy's Machine Learning text, the author claims that multinomial logistic regression has $O(K^2 V^2)$ parameters, where $K$ is the number of discrete ...
1
vote
0answers
23 views

What are the most interesting, new hot topics in machine learning for seminar and later for thesis? [closed]

I'm in an informatics master student in Palestine Polytechnic University, I have a seminar course this semester i cant decide the topic to search in, especially that i want it to be my thesis topic ...
0
votes
0answers
18 views

Convolutional Neural Network Performance - Cats & Dogs

I am currently experimenting with a Convolutional Neural Network, trying to get a good performance on the Cats & Dogs challenge at Kaggle. By now, the best result I could get using my network was ...
0
votes
0answers
3 views

removing batch effect when combing patient's data into a large cohort

I have some clinical data quantifying severity of disease for patients from 3 different hospitals. Basically, the patient severity vector for each hospital looks like below: ...
-1
votes
0answers
20 views

Suitable Model for predicting flight delays in R [closed]

I want to predict the flight delays.Which classifier or which machine learning algorithm i have to use for predicting the flight delays in R and please guide me how to find the accuracy of that ...
4
votes
1answer
176 views

Why do we divide by the standard deviation and not some other standardizing factor before doing PCA?

I was reading the following justification (from cs229 course notes) on why we divide the raw data by its standard deviate: even though I understand what the explanation is saying, it is not clear ...
3
votes
1answer
21 views

Bias/variance tradeoff tutorial

I'm looking for a good tutorial about bias/variance tradeoff. In particular, I'd like to find someone that explains how different algorithms in machine learning play in this tradeoff, and possibly how ...
0
votes
1answer
51 views

Summer school on data mining & ML [closed]

I'm a PhD student in Physics and this summer I'd like to attend a one/two weeks summer school on data mining and machine learning. Do you have one to recommend? Thanks!
0
votes
2answers
27 views

Machine learning algorithms for continuous response variables? [closed]

It seems like common ML algorithms like SVM, Naive Bayes, Neural Nets, Logistic Regression, etc. are designed to predict categorical responses, ie. (1,0). However, I haven't run into an algorithm that ...
-1
votes
0answers
20 views

Tutorials on main machine learning algorithms [closed]

I was asked during an interview to give my favourite machine learning algorithm and describe it. For different famous algorithms (like decision trees, svms etc), which paper would you suggest to ...
0
votes
1answer
37 views

combining multiple classifiers common features

Can multiple binary-classifiers be combined to produce a final output if their feature sets have some common elements? How will this influence the accuracy?
0
votes
2answers
26 views

Emphasize a link between two predictor variables (Machine Learning)

I am creating a machine learning application which will utilize logistic regression (though I haven't ruled out bayesian regression). I have multiple predictor variables that I believe to be ...
3
votes
2answers
79 views

Kernel density estimation vs. machine learning for forecasting in large samples

This is a hypothetical and pretty general question. Apologies if it is too vague. Suggestions on how to better focus it are welcome. Suppose you are interested in the relationship between one ...
0
votes
0answers
3 views

When to use index and seeds arguments of train() in caret package in R [migrated]

Primary Question: After reading the documentation and google searching, I am still stumped as to what the situations are where it is advisable to pre-define resampling indices such as: ...
-1
votes
0answers
9 views

Academic source for precision/recall/F-Score [duplicate]

I know that precision/recall/F-Score are widely used to evaluate Machine Learning algorithms' performance. I also want to use it for my Master's Thesis and I am searching for an appropriate source to ...
0
votes
0answers
24 views

SVM fusion training data set

For a binary classification problem, I have split the data set into multiple sets and trained each set using a SVM. I want to combine the outputs from each data set using another SVM. What is the best ...
0
votes
0answers
26 views

Statistical comparison of multiple prediction models

I have a rather limited data set where for 100 subjects 30 attributes were measured before surgery and one attribute ($y$) was measured after surgery. About 20% of values are missing. The goal is to ...
1
vote
1answer
17 views

Name and methods for classification with 'unknown' as acceptable result

What is it called when, in a classification task, it is acceptable that some data-points do not receive a label? And what classifiers are suitable? I have a dataset with a two valued target variable. ...
1
vote
2answers
48 views

Should image classifier be trained using colormap pixels or the actual value?

For example, I have a population density map of a 100 x 100 km square region. Each part of the rectangular region represents the population density i.e. (1,1) -> 128 people, (100,100) -> 50 people ...
0
votes
0answers
13 views

Non idependence within groups

I have to train a machine learning model for classifying two groups. Unfortunately, my positive group has a small number and many cases are not independent from each other (observations taken in ...