Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

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.

0
votes
0answers
2 views

What does the intercept represent in a model matrix?

I am making a KNN algorithm to predict close_price with about 80,000 rows of this data. ...
0
votes
0answers
11 views

relation among loss function / MLE / Bayesian estimation

I have read a lot of stuff on the relation between minimizing a loss function / maximizing the likelihood / choose a centrality measure of the posterior (Bayesian estimation); but I cannot see a clear ...
0
votes
0answers
8 views

Haul's Correlation-based Feature Selection (CFS) formula spread

I want to use the Correlation-based Feature Selection (CFS) proposed by Haul. I found this formula where $r_{zc}$ is the correlation between the summed components and the outside variable, $k$ is ...
0
votes
0answers
12 views

Is Stochastic Gradient Descent sensitive to training permutation?

I've recently read that SGD (Stochastic Gradient Descent) is one of the most popular techniques for training Machine Learning algorithms, including DNNs (deep neural networks). However, my ...
0
votes
0answers
7 views

What is parameter chaining in CNN?

I have read an article about the benefits of CNN. One of the points was "parameter chaining". What does it mean? And how does it make CNN more convenient?
0
votes
1answer
17 views

What are general practises used to divide the data into training / dev and test set?

Example: I have am building a dog vs cat classifier and I have collected data from 15 countries. Europe: 1. UK 2. France 3. Germany 4. Italy 5. Finland Asia: 1. India 2. China 3. Japan 4. Russia 5. ...
0
votes
1answer
15 views

How can I visualize and correctly interpret the multi-output of a random forest regression?

I have multiple inputs and multiple outputs for a model I am trying to build using SkiLearn's Random Forest Regression in Python. I have imputed the missing data, divided the columns where the Ys ...
0
votes
0answers
21 views

What to choose?ML project or an Internship? [on hold]

This is slightly off topic but pretty serious for me. I am an undergraduate student in CSE, 3rd year. I am confused in whether to do internship or to make my own project in Machine Learning in my ...
0
votes
0answers
13 views

Manifold in the context of machine learning

In the Deep Learning book by Goodfellow et al. on page 158 it is stated: In the context of machine learning, we allow the dimensionality of the manifold to vary from one point to another. This ...
0
votes
1answer
17 views

Practical interpretation of Precision-Recall AUC

I have a classifier with an AUC (PR) of 0.06 which I will use for a practical interpretation. My test set consists of three months of data with a total of 2,200,000 observations of which 0.03 are ...
1
vote
1answer
18 views

Predict song genre using LSTM

I have a dataset of songs based on genres. For example, a song may hold {5, 2, 3} as scores set for Sentimental, Rock and Jazz. In total there are 800 songs sequentially arranged. I want to predict ...
0
votes
0answers
11 views

What is the relationship between stochastic mirror descent and stochastic gradient descent?

I don't know much about stochastic mirror descent and was wondering if someone could briefly summarize it in general terms and compare/contrast it to stochastic gradient descent. When I understand ...
0
votes
1answer
21 views

Determine if groups have significantly different metric values

I am familiar with using ANOVA to analyze differences among group means. However, I am interested in analyzing differences for metrics other than the mean. Is anyone aware of a statistical test that ...
1
vote
0answers
17 views

Partial Collinearity in Regression

I had a doubt about the effect of multi-colinearity in regression analysis. I understand if two variables are co-related we cannot disentangle the effects of one from the other on the target variable ...
0
votes
0answers
3 views

Setting bias of output layer for imbalanced datasets

From a blog post from Andrej Karpathy on training neural networks: Initialize the final layer weights correctly. E.g. if you are regressing some values that have a mean of 50 then initialize the ...
0
votes
0answers
9 views

how to take a subset of a dataset to fine-tune a neural network?

I would like to build a classifier with 80 000 images and 45 classes. As each epochs takes 1 hour to train, Is there a way to win time by training only a subset of the dataset without lowering the ...
0
votes
0answers
5 views

Probability of Incurring Maximum Loss

In online classification one can use mistake bound learning, where one assumes that all $y$ are generated by some target mapping $h^*: \mathcal{X} \rightarrow \mathcal{Y},\,\, h^* \in \mathcal{H}$. ...
0
votes
0answers
15 views

Calculating the number of neurons and the number of hidden layers for a neural network MATHEMATICALLY

I have a fair idea that a lot of research has been done and is still underway to explore the science behind the black art of a neural network (NN) architecture, i.e., accurately calculating the number ...
0
votes
0answers
7 views

using latent dirichlet allocation to reduce the number of dimensions in bag of words model?

Does anyone have experience reducing the dimensions in a traditional bag of words model? For example, if you want to train a decision tree on a large set of reviews, the size of the vocabulary ...
-2
votes
2answers
44 views

how to analyze time series data and mark if single data is seasonal or not seasonal

I have data set as shown. It is daily sales data for 4 different product for almost a year. I aggregated the sales of product for each day into . I plotted sales of 4 product as per date and got this ...
2
votes
0answers
23 views

Gaussian process and its limitations

I once saw the following statement on Gaussian process, ...
4
votes
1answer
32 views

What is the relation between a surrogate function and an acquisition function?

A surrogate function is a simpler function than the objective function to evaluate. An acquisition function is used to propose sampling points. In the context of Bayesian optimisation and Gaussian ...
0
votes
0answers
11 views

When is the sum of model predictions the prediction of the sum?

The response variable in a regression problem, $Y$, is modeled using a data matrix $X$. In notation, this means: $Y$ ~ $X$ However, $Y$ can be separated out into different components that can be ...
0
votes
2answers
9 views

Correct way of getting generalizaton performance of a model using the whole dataset

Standard practice is to split data into a train/test set, then use the train set for hyperparameter tuning / model selection, using for example cross-validation over the whole training set. Finally, ...
0
votes
0answers
23 views

How to solve MAP problem with images (EHT Bouman's Paper)

I'm not familiar with deep learning. Only know some basic concept about Neural Network. Recently I've tried to figure out the algorithm used to restore Black Hole image. After lot's of searching, I ...
0
votes
0answers
5 views

Methods to predict a binary outcome with ordinal covariates

Just a very general question: what are the most efficient methods to predict one single binary variable $Y$ using a set of ordinal covariates? In my precise case, I have around twenty ordinal ...
0
votes
0answers
7 views
1
vote
1answer
61 views

How to determine number of profile in a dataset derivated from repeated measures?

I'm currently working on datasets which have been derivated from repeated measures over time (blood concentrations). Actually the descriptors of these datasets are descripting the shape of the curves (...
0
votes
0answers
7 views

overfiting validation set increase model performance

I'm using CNN for image classification on an unbalance data set. (e.g class A = 1000 image, class C=50 image). I got 16 class. I'm using class weights and in total i have less than 3500 images. I do ...
0
votes
0answers
23 views

Bayesian Linear Regression to Gaussian Process

I'm trying to understand how a Gaussian Process with a squared exponential covariance function can be obtained from Bayesian Linear Regression with a Gaussian prior $N(0,\sigma_p^2 I)$ on the ...
0
votes
0answers
6 views

How to create a heirachical classification using hash table in python? [on hold]

I have tried to implement a classification just like amazon for another taxonomy. but i dont know how it is done. my question is about how to create a hash table in python Example : ...
1
vote
1answer
11 views

if different methods have difference 0.5 in third decimal place while finding accuracy then what to conclude?

For the comparison of different feature selection methods and evaluating performance metrics. After evaluation when their is only 0.5 difference in third decimal place. Is this difference is ...
0
votes
0answers
18 views

What is a sparse Gaussian process?

In the paper Junction Tree Variational Autoencoder for Molecular Graph Generation, section 3.2, the authors state that they train a sparse Gaussian process to predict a chemical property, $y(m)$, of a ...
0
votes
1answer
24 views

How to use features in regression model with 2 of them in linear relation with the value to be predicted?

I am relative newbie to data science so please excuse me if its a trivial question. I have 6 features and want to predict the 'y'. These features are related to y in the training data-set as follows; (...
0
votes
0answers
36 views

Machine (supervised) learning and board game [on hold]

Let's assume there's a board game like chess or go (in other words, perfect information game). We don't know how to write a good evaluation function for this type of board games, but we have a lot of ...
1
vote
1answer
46 views

VAE: why we do not sample again after decoding and before reconstruction loss?

In many of the VAE schematics and in the original paper, a sampling step is present after decoding and before the reconstruction loss as shown in the image below. The image comes from Stanford CS321n. ...
0
votes
0answers
7 views

Is pooling acceptable to evaluate information extraction?

When dealing with information extraction of unbalanced classes (e.g. the desired class has a prevalence of 0.5%), the required sample size for validation might be huge (thousands of cases and more), ...
0
votes
1answer
33 views

What will go wrong if we apply linear or other types of regression to translate sentences between two languages? [on hold]

DISCLAIMER: I also asked this at- https://datascience.stackexchange.com/questions/52056/what-will-go-wrong-if-we-apply-linear-or-other-types-of-regression-to-translate, as I didn't get any response ...
0
votes
0answers
9 views

Improveness given a certain AUPRC

I am training a machine learning model (Random Forest) for a multiclass problem (64 classes) in which most of them are highly imbalanced. That's why I am using mainly F1 score for checking the model's ...
0
votes
0answers
19 views

How to add new features to already trained model without training again on whole dataset?

Suppose, we have following features on which a classification model (Neural Network) is trained to predict whether a customer will buy Milk or not (0 :Will not buy, 1:Will buy) each week(n): ...
0
votes
0answers
14 views

Gradient clipping just before averaging

A typical way of implementing mini batch learning is by calculating the gradients of every element within the mini batch and then average all of these element's gradients to come up with the final ...
1
vote
0answers
28 views

Why aren't auto-encoders also considered generative models?

Auto-encoders (AEs) are composed of an encoder and a decoder (often represented by a neural network). The encoder produces a vector representation $z$ of its input $x$ (e.g. an image). The decoder ...
1
vote
0answers
19 views

What is the relation between message passing and probabilities in Bayesian inference?

The belief propagation algorithm is a message passing algorithm that can be used to estimate marginal probabilities on Bayesian networks. What is the definition of these messages? What is the ...
0
votes
0answers
5 views

Time Scale of Evidence in Evidential Reasoning Approach

Long shot here, but can anyone point me in the direction of information on the effects of evidence corresponding to different lengths of time when using the Evidential Reasoning Approach (Dempster-...
0
votes
1answer
37 views

A model (neural network) for sets of arbitrary length [on hold]

I've been searching for a model that is close to RNN (is well suited for investigating sets of arbitrary lengths) but is insensitive to order. I'm aware of bidirectional RNNs. I've also found a 'bag ...
0
votes
1answer
34 views

Training error less than validation error, but higher than test error?

I have a time series regression prediction problem. So I divided the dataset into 3 parts: training (first 70% of the time series data) validation (from 70% to 85% of the time series data) test set (...
0
votes
0answers
17 views

Assigning probabilities to ensemble experts (classification)

Suppose we have a set of experts which predict on a data set, and the true labels are also given. I would like to find out the probabilities for combining predictions of separate experts. So the ...
2
votes
1answer
14 views

Reference Request: Proof of Early Stopping Criterion

I am looking for a proof that "Validation-based early stopping" methods work but I have no idea where to start, as I am new to this field. Any recomendations of some rigerous papers that focus on ...
0
votes
0answers
14 views

Why does 4-gram work better than trigram or bigram or unigram in my experiments?

In a binary classification task, I used Logistic regression, decision tree and Adaboost with decision tree (max_depth=1). For each of the machine learning task, I used GridSearchCV to choose the ...
0
votes
0answers
8 views

Metric learning with respect to an outcome

Suppose I have $n$ datapoints in $p$-dimensional space, and the $p$ variables are highly heterogenous. That is, there is no natural way to combine them. Some are ordinal, some one-hot, some continuous,...