Stack Exchange Network

Stack Exchange network consists of 174 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]

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

1
vote
1answer
11 views

Terminology for neural networks

The words “a neural network” in machine learning can refer to either of The architectural design of a neural network (number of layers, etc) The network with specific parameter values encoded in it. ...
0
votes
0answers
9 views

PCA influence of duplicates

I am using sklearn IPCA decomposition and surprised that if I delete duplicates from my dataset, the result differs from the "unclean" one. What is the reason? As I think, the variance is the same. ...
0
votes
0answers
7 views

Gradient Descent for non linear model fitting in R [on hold]

I need to fit a model in R using Gradient Descent. The model is a non linear model. Is there any package implementing gradient descent in R?
0
votes
0answers
8 views

How to create the initial ensemble samples for EnKF

As we know, for the ensemble Kalman filter (EnKF), we need to create a set of samples in the beginning and then to run the predict and analysis step. But for now I have a question of how to create the ...
6
votes
5answers
445 views

What precisely does it mean to borrow information?

I often people them talk about information borrowing or information sharing in Bayesian hierarchical models. I can't seem to get a straight answer about what this actually means and if it is unique to ...
0
votes
0answers
6 views

Finding Impact of IV on NPS of response to a survey [duplicate]

I have a dataset like this. Where the first column is the age of usage of product of a user (in days) and second column is the response of the user to the typical NPS survey question: Using these ...
0
votes
0answers
9 views

Cross Correlation between two RVs and PCA

What is the difference between the maximum value of cross-correlation value of RVs X, Y and maximum eigenvalue of Covariance matrix of these same RVs X and Y? Are both same and just represents the ...
1
vote
2answers
208 views

What is the name for the complement of accuracy?

I have a metric that is defined as $1 - Accuracy$ and I need a name for it. Is there a scientific name for the complement of accuracy?
0
votes
0answers
5 views

Training model with large range for target variable [on hold]

I am training a model using R and have a specific issue with a target variable whose values vary from 10n to 10m (6 orders of magnitude). I took a log transform before training the model and the error ...
1
vote
0answers
11 views

Convergence criterion for R-learning algorithm

I'm trying to find a policy for a simple game using R-learning algorithm. I have a field with values (agent can move in 4 directions) and the goal is to get from starting point to finish point with ...
0
votes
1answer
16 views

A question about pca and gene function analysis

I'm new to bioinformatics, and I have a pretty basic question. Let's say I have a bunch of genes {Xi} and I want to know which one has the most significant on some measurable phenotypic trait Y. Now I ...
0
votes
0answers
15 views

Why use absolute value of the gradient for saliency maps?

Simonyan et al. 2014 approximate a neural network locally by a linear function and take the weights of this approximation as a measure for support of a specific class. Can someone explain to me why ...
0
votes
0answers
31 views

validate residuals plot [on hold]

I have data with a (rotational speed) and b (speed) features. The target feature (t) is a kind of consumption. I want to fit a model in order to predict power from these two features. In the code ...
0
votes
1answer
26 views

Data level at which the Regression should be run

So I am new to regression and I have a basic doubt: Let's say I have 100 unique products(product id) which have a lot of other features that contribute in calculating the product_price(dependent ...
1
vote
0answers
13 views

What is the difference between Generative Adversarial Networks (GAN) and Generative Antagonistic System (GAS)?

What is the difference between Generative Adversarial Networks (GAN) and Generative Antagonistic System (GAS) in the neural network?
0
votes
0answers
7 views

R quantstrat backtest faq [on hold]

I am new to R and is exploring quantstrat for backtesting purposes. I have some fundamental question that I really hope someone can assist. From my understanding, quantstrat only evaluate the ...
1
vote
0answers
20 views

How cost function for simple linear regression behaves under different settings with batch gradient descent?

In the linear regression problem, using a simple linear model with 1 variable & with 2 model parameters, performing batch Gradient Descent(GD) & assuming I am using Mean Square error as my ...
1
vote
0answers
13 views

With two deep learning models, how do I perform Bayesian Model Averaging for better prediction on a test set?

Given two deep learning models that can predict on a test set, what I want to do is use BMA (Bayesian Model Averaging) to average the models to better predict? What exactly is the procedure for this? ...
0
votes
0answers
15 views

Finding effect of a variable on NPS of a survey responses

I have a survey responses data. It has various columns, but one of the column is the age of the product usage by the user. The other column is the response given by the user on a 0-10 point scale as ...
1
vote
0answers
21 views

Regression with a high number of 0's for target variable. How do I approach this?

I have a dataset where the probability of an event happening is very low (15%-20%). When the event happens, there's a dollar amount attached to it. The distribution is very right skewed, ranging from -...
0
votes
1answer
21 views

Imbalanced multiclass classification with many classes

I am working on a text classification project in which we have hundreds of (imbalanced) classes. Some characteristics of the data: We have examples of "bad" documents. Basically documents that don't ...
0
votes
1answer
32 views

How to calculate the output from this neural network

bias w0=0.15 and w01=0.5. Assume the intercept of the combination function is 0. Basically, I am studying for my exam and I don't understand how to calculate this question about neural network: 1) ...
0
votes
0answers
13 views

How to choose regression algo without validating each algo? [on hold]

I see some regression algo, one is in sklearn.linear_models and the other one is in sklearn.ensemble eg. random forest regressor. I'm confused with how to choose the algo in the first step without ...
1
vote
1answer
15 views

Word for loss function except weight regularization?

A typical loss function in machine learning is: $$L(\theta,x) = \mathcal L(\theta,x) +\sum_{\theta} |\theta|$$ I typically use the word “loss function” both for $L(\theta,x)$ and for $\mathcal L(\...
0
votes
0answers
16 views

Different result while training in CPU and GPU for Google BERT

I was running few examples exploring the pytorch version of Google's new pre-trained model called the Google BERT. I ran the example in both CPU as well as GPU machines. I run the following code for ...
0
votes
0answers
19 views

I'd like to do regression using canonical correlation analysis

I got two multidimensional datasets, X and Y. I thought I build the model, which explains the relationship between two datasets, using canonical correlation analysis (CCA). The first correlation ...
0
votes
0answers
9 views

Imbalanced class SVM prediction results using different validation data

I am trying to fit my data to a classifier using SVM. My data has 2 classes, the positive class which occurs with a probability of 0.002 and the negative class which is the dominant one. Suppose that ...
0
votes
0answers
9 views

Is harmonic mean of feature importance index a statistically appropriate approach to obtaining most important features across different models?

I've trained 16 different models on similar biological datasets to predict the occurrence of a specific disease (the target) from ~18000 biological super-pathways (features). Each dataset has the same ...
0
votes
0answers
17 views

Query on Logistic Regression error function

I am trying to understand the differences between Logistic Regression & Linear Regression and the answers here explains it very nicely. But, I had a question related to the logistic regression ...
1
vote
1answer
33 views

Computing KL divergence in loss function of Bayesian neural networks

Hi I am trying to understand how the loss function for Bayesian Neural Networks (BNN) is computed. In the TensorFlow documentation they illustrate a BNN in practice where they train the network to ...
0
votes
0answers
27 views

If I remove 20% of the train examples, my CV and train score improves, how can I find the reason why?

I have a small dataset - several thousands examples with a lot of features, a lot of them have a lot of zeros. If I remove 20% of examples from the end of the dataset - my CV and train(on changed ...
0
votes
0answers
18 views

Find correlation of a categorical variable with a continuous variable

I have a categorical variable which takes 5 different values; I have done a hot-encoding on it and converted that into 5 different variables, each taking 0 or 1. I'd like to find the correlation ...
0
votes
0answers
10 views

MAPE changes when unnormalizing the data

I'm doing some regression analysis and in the preprocessing of the data first I'm taking log1p and then I'm normalizing the data. When done like that I'm getting MAPE around 0.94 % bu when I'm ...
-1
votes
0answers
4 views

Saving and loading a model with UMAP [migrated]

I use UMAP for visualization similar to t-SNE. I was thinking to try training and testing a certain dataset. I dig into the UMAP documentation without finding any way of saving the models. Is there ...
0
votes
1answer
17 views

Is `sigmoid` required for binary cross entropy?

I have a DNN that has to predict whether an input belongs to a class or not. During training, I use binary cross entropy as a loss function. I noticed that if my ...
1
vote
0answers
24 views

Question about sample size for each class for machine learning classifiers

I'm trying to use a machine learning classifier (SVM in particular) on data that I generate. Unlike other applications, the data is not given to me but rather I have the flexibility to generate how ...
2
votes
1answer
14 views

How to get model in knn()?

Given I have classified my inputs using R's built-in knn(): ...
1
vote
0answers
23 views

Recommended books about neural networks [on hold]

what books do you recommend on neural networks? We can think of a few categories: 1. A python recipe book 2. A general introduction book 3. An Updated book 4. Specialized book on CNNs 5. Specialized ...
1
vote
1answer
41 views

Best model to predict if the client will buy our product or not

I would like to find a good model to predict which client will buy my product in 2018. I would like to have opinions on which method can fit my data to predict which client will the product A in 2018. ...
0
votes
0answers
10 views

Best performance metric for balanced datasets (two clases)

starting off, I have a highly IMBALANCED dataset. But I managed to balance it using SMOTE technique. For IMBALANCED, I consider F-Measure. But I realized that since I balanced the dataset, perhaps ...
13
votes
3answers
549 views

How is causation defined mathematically?

What is the mathematical definition of a causal relationship between two random variables? Given a sample from the joint distribution of two random variables $X$ and $Y$, when would we say $X$ causes ...
0
votes
1answer
26 views

How Probability distribution relates to neural networks?

The concept of random variables and probability distributions are confusing in the context of neural networks. In a neural network, which is the random variable and what is the probability ...
0
votes
0answers
15 views

Why is the F1 score so similar to Cohen's kappa coefficient for imbalanced data?

I am exploring a performance metric to use for my imbalanced dataset. In the process, I noticed something interesting about the similarity between Cohen's kappa score and the F1 score. The two metrics ...
0
votes
1answer
20 views

Dealing with dataset imbalance: test if adjusting is necessary

I'm currently working on a project which uses a imbalanced dataset (two classes) for training, and I'm not sure if I should do a resampling procedure or not. Is there a way to actually test if it's ...
0
votes
0answers
23 views

Keras giving memory allocation error and running extremely slow [closed]

I am working on character recognition using convolutional neural networks. I have 9 layer model and 19990 training data and 4470 test data. But when I am using keras with Tensorflow backend. When I ...
1
vote
0answers
24 views

Predictive models to predict sales with r

I would like to find a good model to predict which client will buy my product in 2018. I would like to have opinions on which method can fit my data to predict which client will the product A in 2018. ...
0
votes
0answers
20 views

How important is research on model selection methods in Statistics?

My question is nothing technical. I just wanted your opinion on how important is the model selection problem in the field of Statistics considering the age of big data. Are the current methods such as ...
1
vote
1answer
14 views

When will Naive Bayes misclassify continuous training instances?

For the discrete case, we can say that Naive Bayes might misclassify training data due to things like the zero-frequency problem. Why might Naive Bayes misclassify continuous training data?
0
votes
0answers
7 views

How to paraphrase and augment training data for a question answering ML model?

I have only 50 question, answer pairs in my training data, where each question represent a unique intent. However, the training data is too small to build any meaningful ML model. What are the ...
-1
votes
0answers
5 views

Hands on prediction models using paradigms from a matrix that contains leds

I was interested in learning prediction models using paradigms in order to observe if there is a difference using different methods. The idea is to use multiple 6x6 matrices that contain 0/1 data in ...