Questions tagged [machine-learning]

Machine learning algorithms build a model of the training data. The term "machine learning" is vaguely defined; it includes what is also called statistical learning, reinforcement learning, unsupervised learning, etc. ALWAYS ADD A MORE SPECIFIC TAG.

Filter by
Sorted by
Tagged with
2
votes
1answer
1k views

Size of the Hypothesis Space

(I'm asking the same question as the one linked below, I simply don't have enough reputation to comment yet, but hopefully, this one will more clearly explain what me and the other asker both mean) ...
0
votes
1answer
793 views

SegNet CamVid dataset training classes mismatch?

This is with reference to the CamVid dataset and one of its tutorial here: http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html I'm quite confused by how the model is supposed to be trained on 11 ...
0
votes
1answer
30 views

Is there a way to generate artificial data from clusters?

Suppose you have a data set that can be clustered as follows: Is there a way to generate data that would fit inside, say, the red bubble, or blue bubble? This can definitely be done in two-dimensions,...
2
votes
2answers
57 views

Why does the linear regression algorithm assume the input residuals (errors) to be normal distributed? [duplicate]

I am trying to know the assumptions of linear regression (LR). I understand linear regression needs the relationship between the independent and dependent variables to be linear, but LR also assumes ...
0
votes
1answer
16 views

How do autoencoders reconstruct images/color?

I am abit confused by how autoencoders are able to reconstruct colors in images. According to me a CNN has feature detectors that convert the image into a sequence of feature or activation maps. These ...
3
votes
0answers
62 views

The extrapolation problem: model selection, performance metrics, and improvement

Machine learning models are fit to a response variable within a given range. This leads to weak and sometimes disastrous performance when it comes to instances with an actual response variable outside ...
1
vote
0answers
44 views

What causes cost function to have convex and non-convex nature?

I am understanding gradient descent and i just stuck at logistic regression. For gradient descent to converge to global optima we would require hypothesis to have linear function so that it can cause ...
0
votes
0answers
20 views

Is there a way of obtaining 95% confidence intervals for the bias-corrected estimate of the c statistic?

I ran a binary logistic regression and then used the boostrap internal validation procedure, implemented in Frank Harrel's RMS package in R. I saw a couple of studies having used boostrap validation ...
0
votes
1answer
41 views

Are Epochs, Learning rate and Hidden units related to each other?

I'm working on an LSTM NN, I wanted to know if there is any relationship between the learning rate, epochs and the hidden units that will/might affect my classification output? The MATLAB version I'...
0
votes
1answer
44 views

Machine Learning alternative for hashing [closed]

Is there a Machine Learning technique that can used to detect the slightest change in data? I know this can be done using a hash but I was just wondering if there is any machine learning technique out ...
0
votes
0answers
27 views

Neural Network - Choosing best model - But what about epochs?

I am trying to construct a neural net. I have several questions about the procedure. I can get results from a manual model, by switching parameters with my instincts and running each time. I am using ...
1
vote
0answers
59 views

What model should I use to estimate students underlying ability?

As an experimental project, I'd like to estimate around 1000+ students 'underlying ability' or essentially their likely future performance in tests. The structure of the experimental data is as ...
0
votes
1answer
258 views

How to deal with mixed data type in deep neural network?

My dataset has 300 numeric features, each of them ranges from 1 to 500. In addition, I have 1000 categorical features (0 or 1), around 90% are 0's (kind of sparse). To run deep neural network, I ...
1
vote
1answer
148 views

Help understanding Linear Model in ESL book

Also known as "Nate slowly deciphers ESL to conceptual understanding/plainer language", part two (see part one) Help me understand this (bullets added) The term $\hat{β}_0$ is the intercept, also ...
1
vote
1answer
150 views

How to apply the output layer function in a neural network [on hold]

I am implementing a Neural Network in a somewhat different fashion. I train my neural network locally using a small subset, and export the weights. My goal is to test the neural network in a ...
2
votes
1answer
34 views

Regression with summary statistics

The following setting should already be familiar: Let $X$ be some space, $\mathbb R^d$ for simplicity, and let $Y\subseteq \mathbb R $. An unknown distribution $\mu $ is defined over $X\times Y$ and ...
0
votes
0answers
28 views

Bellman's Equation confusion

I have read this Confusion around Bellman (update) operator and yet I am not clear about the difference between the two equations $V^{\pi }(s)=R(s,\pi (s))+\gamma \sum _{s'}P(s'|s,\pi (s))V^{\pi }(s')....
0
votes
0answers
17 views

Interpolate/Impute Time Series Data from another Time Series

I have a dataset of multiple lakes with water level elevations through time. The observations are not regularly spaced and have many large gaps. Further, some of the older observations may be of lower ...
0
votes
2answers
1k views

Machine learning method to determine continuous values from discrete and continuous parameters

I watched online courses about multivariable linear regression which addresses the problem of determining values from numeric inputs. Like, predict prices for houses based on age, size, number of ...
1
vote
1answer
47 views

Understanding the reproducing property of RKHS

I am currently trying to learn about Reproducing Kernel Hilbert spaces (RKHS) and would like to gain some intuition about its reproducing property. The RKHS is defined with kernel $k(x,x')$ which maps ...
1
vote
1answer
28 views

What is the difference between Zero Shot Learning and clustering?

I recently found out about ZSL and to me, it is very similar to a clustering algorithm with one difference: a clustering algorithm such as DBSCAN doesn't need to have a pre-defined group of feature ...
0
votes
0answers
13 views

How to get change of basis matrix for Canonical Correlation Analysis?

A bit of background: I am trying to create toy example of the Curds and Whey regression shrinkage algorithm in python. In a standard multivariate regression this algorithm uses canonical correlation ...
0
votes
2answers
31 views

Compare two Roc curves with same Auc

I have 2 churn prediction model. Both provided very similar AUC values for Roc but with different shape. How should I assess which to choose based on that fact?
7
votes
1answer
4k views

Unscented Kalman filter-negative covariance matrix

I have recently started working on the unscented Kalman filter. I coded the numerically stable version (i.e., square root Kalman filter) and used MATLAB for implementing. In the final update step, ...
28
votes
2answers
11k views

What does the term saturating nonlinearities mean?

I was reading the paper ImageNet Classification with Deep Convolutional Neural Networks and in section 3 were they explain the architecture of their Convolutional Neural Network they explain how they ...
0
votes
1answer
65 views

Now that I've theoretical foundation in ML, where can I find simple, already solved, practice exercises to better my understanding of data science?

I've studied and understood well quite a bit of theoretical concepts of Machine Learning (except Deep Learning): e.g. the mathematics behind several classification and clustering algorithms, SGD and ...
1
vote
0answers
22 views

Data splitting with caret: Can we remove the ID Coloumn after folds are created?

so we have a dependent sample (two observations for each participant). To prevent data from one participant being in the training set and in the unseen fold in cross-validation we used the groupKFold ...
3
votes
1answer
43 views

Rare value prediction in Regression

Im working on a project which is to estimate blood pressure from independent variables. The problem I have is that the Blood Pressure data is gaussian in nature since most of the people are having ...
0
votes
1answer
762 views

Forward search feature selection and cross-validation

I've a question regarding forward search for feature selection. Basically, I've found here and here that the procedure is the following: As the procedure suggests, the cross-validation is applied ...
1
vote
0answers
10 views

To Find the variance of the classifier on different datasets,How does this formula come out?

To Find the variance of the classifier on different datasets, we assume sampled predictions have variance $σ^2$ and correlation $ρ$. How does this formula come out? $$ \text{Var} (\frac{1}{m}\sum_{i=...
4
votes
0answers
21 views
0
votes
0answers
31 views

My predictors are all categorical variables but the dependent is numerical, how to eliminate dummies?

My predictors are all categorical values but the dependent is numerical. How can I eliminate dummies if I use a linear regression model? The values are tough to solve with backward elimination; ...
4
votes
1answer
661 views

Formula for marginal probability in CRF++

On the website for CRF++ http://crfpp.sourceforge.net/ they mention that marginal probabilities can be output for each possible label. My question is, in CRF theory, what's the formula for this ...
0
votes
0answers
15 views

way to transform reinforcement learning problems to bandit problems

I wonder what a general way looks like to transform reinforcement learning problems to bandit problems (especially contextual bandit problems) Thank you!
1
vote
1answer
153 views

Why is it hard for a neural network to learn the identity function?

I wanted to see if a neural network could learn the identity function using the MNIST handwritten dataset. Here is the full code ...
0
votes
0answers
7 views

Using CNNs for template matching in multi-channel image?

I was wondering if it's possible to train a CNN to recognize similar parts between different images. Here's my problem: let's say I have different images that overlap in part to form a larger image (...
8
votes
4answers
5k views

Matthews correlation coefficient with multi-class

Matthews correlation coefficient ($\textrm{MCC}$) is a measurement to measure the quality of a binary classification ([Wikipedia][1]). $\textrm{MCC}$ formulation is given for binary classification ...
2
votes
2answers
72 views

What is after doing k-fold cross-validation?

When we do K-fold cross validation, we are testing how well our model is able to get trained by some data and then predict data it hasn't seen. I selected 9 fold for training, and 1 fold for ...
2
votes
1answer
254 views

Area Under the Precision Recall curve -similar interpretation to AUROC?

I am trying to interpret the AUCPR. Say I have the following Precision-Recall curve. Firstly: It ends at 0.38 on the y-axis because this particular plot has ...
0
votes
1answer
41 views

How to check if a Machine Learning model is applicable for newly input data?

Suppose we have a good Machine Learning model, with good cross-validation and test score. How can we estimate whether a newly input data instance belongs to the domain of data where model predictions ...
0
votes
0answers
13 views

Understading Overfitting from Precision and Recall scores

Can I understand if my model is overfitting or underfitting from its precision and recall scores that it has on training and test datasets?
1
vote
1answer
25 views

Only one global minimum for univariate linear regression squared error cost function? [duplicate]

I'm going through the Stanford AI course on Coursera (like many others with similar questions). For univariate linear regression, supposedly there is only one (global) minimum for the cost function (...
6
votes
2answers
4k views

Is it ok to get negative Cosine Similarity using LSA?

I am getting negative cosine similarity value between two documents in Latent Semantic analysis. How should it be treated?
0
votes
1answer
35 views

Why do we connect convolution layers in sequence instead of applying them separately on input image?

I am already aware of the convolution function, CNN and all. I have already implemented a few. But this question strucks my mind every time. Most of the networks I have seen, use a stack of ...
0
votes
1answer
16 views

Can someone give some concrete examples to explain “a probability distribution over a single example” mean?

Section 5.2 of the deep learning book says How can we affect performance on the test set when we get to observe only the training set? The field of statistical learning theory provides some answers....
1
vote
1answer
48 views

In deep learning, what is empirical distribution good for? In the case of applying vgg on mnist, how to use the empirical distribution?

section 3.9.5 of The Deep Learning Book says \begin{equation} \hat{p}(x) = \frac{1}{m} \sum_{i=1}^m \delta(x - x^{(i)}) \tag{3.25} \end{equation} We can view the empirical distribution formed from ...
3
votes
2answers
24 views

How to make train/test split with given class weights

I am doing simple multi class classification ML problem. I was given train data with perfectly balanced classes. However the data I must predict is not balanced. I was able to deduct the class ...
2
votes
2answers
148 views

How can I train my deep learning model on another similar yet different dataset

I am doing semantic segmentation (multi-class classification of image pixels) using convolutional neural networks (CNN) in Keras. In particular, I am applying this to aerial images of crops (...
2
votes
1answer
145 views

ML Method for directional forecast

I've uni-variate demand data (Weekly data for 2 years), and wish to do a directional forecast based on the data. Magnitude of the forecast is not important here, but directional accuracy is of ...
-1
votes
0answers
29 views

Are there any theoretical references on neural network, particularly RNN, CNN and GAN? [duplicate]

I am a Pure Maths PhD student who is interested in learning theoretical neural network, particularly RNN, CNN and GAN. However, most references that I came across focus too much on applications. ...