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
Make your voice heard. Take the 2019 Developer Survey now

Questions tagged [machine-learning]

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

0
votes
0answers
6 views

Using Neural Network to identify similar sentence structure [on hold]

I need guidance for what methods/techniques I can use in nueral networks to group similar sentences. In example if I have the following sentences, how can I group them into 3 groups? ...
0
votes
1answer
14 views

Linear regression feature selection equivalent for a classification problem?

I have the following: Label (y): a boolean flag indicating something is good or bad Features (X): lower-level features that are believed to be correlated with the boolean flag. Some of them are ...
1
vote
1answer
18 views

How can we estimate (conditional) probabilities from a dataset?

Given three random variables $X$, $Y$ and $Z$, how can we estimate $P(X)$, $P(X\mid Y)$ and determine whether $P(X \mid Y, Z) = P(X \mid Z)$ from a dataset (of e.g. $N$ observations) which contains ...
5
votes
1answer
149 views

Using PCA to reduce dimensionality of training and testing data

I've read so many contradicting opinions that I feel like I need to ask the question myself. Say I use PCA on a dataset with 60 variables and find that I can explain 98% of variance with 6 principal ...
0
votes
1answer
20 views

customized loss function

I am trying to solve a regression problem where I have to predict for how long a machine will be out of order given its status when it breaks. The goal is to fix first machines that are predicted to ...
2
votes
1answer
20 views

cant get model info from caret model in R

cant get model info from caret model in R for linear model i can just use the summary function however for this caret ridge model i got strange information this is what i got when i run summary <...
0
votes
0answers
12 views

Why Transformer use little activations?

I am confused about the activation functions used in the famous NMT model Transformer. In other classical networks such as ResNet and LSTM, the activation functions are used after every linear ...
1
vote
2answers
64 views

In Bishop's textbook, is the example of overfitting exaggerated?

Here, the data $x$ are randomly generated, and $t$ are generated by running $x$ through a function $\sin(2\pi x)$, then Gaussian noise is added. Bishop's text then tries to fit those data using a ...
1
vote
1answer
29 views

Variance of sum of dependent random variables

Can you guys help me prove the following: $$ Var[\frac{1}{m}\sum_{i=1}^my_i]=\frac{1}{m}(1-\rho)\sigma^2+\rho\sigma^2 $$ where the sampled predictions ($y_is$) have variance $\sigma^2$ and ...
1
vote
1answer
18 views

Multi armed bandit algorithms failing with un-scaled rewards

I am experimenting with the multi-armed bandit algorithms (namely: epsilon greedy, decaying epsilon greedy, optimistic initial value, upper confidence interval, and Thompson sampling). My reward is ...
1
vote
1answer
17 views

Why increasing lambda parameter in L2-regularization makes the co-efficient values converge to zero

Why increasing lambda parameter in L2-regularization makes the co-efficient values converge to zero? I have just tried to do the math, but it's a little bit rusted. Lets say that we have a simple ...
0
votes
2answers
36 views

Would machine learning techniques help if the linear and nonlinear relationships is so weak?

I have a cross sectional data set at hand contains four predictors to predict one outcome, I employed bivariate analyses to check whether the relationship between the dependent and independent ...
0
votes
0answers
9 views

How can i create an Ngram model using tensorflow? [on hold]

I want to create an Ngram model using tensorflow that reads from a file and gets the ngram of each word. example output: she 12313 he 12312 word 11111 code 10001 programming ...
1
vote
0answers
13 views

Types of Machine Learning algorithms and architectures where only a fraction of the weights are trained per each training step?

I need help for literature review I'm doing: Does anyone know of a paper where a large number ( Over 50% ) of the weights are turned off at each training step ( besides dropout ) ? Or, if there are ...
0
votes
0answers
31 views

DQN agent helped by a prediction model

Suppose I have a regression model that can make predictions on stock price movements for 10 steps ahead. The labels are ...
0
votes
1answer
27 views

KNN regression: Why does my In sample RMSE look like my out of sample RMSE across K values?

I'm expecting the RMSE plot for my KNN regression model to look like the above image but I'm getting the below when running my code hosted here. Any ideas on what could cause this? I believe something ...
2
votes
1answer
19 views

Which metric to use in an ordering problem? auPR / ROC / Lift?

I need to order Users from most likely to perform a binary action X in the next n days, to ...
0
votes
1answer
22 views

Kernelize Linear Regression

We can kernelize Ridge regression as shown in these notes: https://www.ics.uci.edu/~welling/classnotes/papers_class/Kernel-Ridge.pdf. However would it be possible to find a vector $\boldsymbol\alpha$...
0
votes
0answers
7 views

model for short life cycle products using event detection

I would like to make predictions on short life cycle products. I have a dataset with only 52 weeks. The biggest problem of SLCPS is that it is impossible to find seasonality, cyclicity etc. etc. I ...
0
votes
1answer
22 views

How to approach a classification problem when the sample size is only about 50

I was given a data consists of 53 people and I was asked to come up with a general classification rule based on biomarkers that can be used to classify each person under one of the three possible ...
0
votes
0answers
8 views

Measure Naive Bayesian Classifier certainty and error of prediction

So I am fairly new to this so please be patient :) I am using Naive Bayesian Classifier to find the probability of a class (Yes), then I use this probability in another process. Now I am being asked ...
0
votes
0answers
12 views

Remake predictive model from Bagged trees (ipred) to Random Forest (ranger) [on hold]

I need You help in solving a my problem. I have a working Bagged trees model. However, in large areas, the calculation time is very long. Help, please, remake this example for the random forest model ...
0
votes
0answers
18 views

Why AdaBoost works exactly the way it does

I understand the basic idea of AdaBoost -- when training weak classifiers, use more of the difficult examples. However, it puzzles me why I sould modify the weights the way AdaBoost does. There are, ...
0
votes
1answer
15 views

Reinforcement Learning: Actor Critic - Why is weight sharing possible?

I was looking at Open Ai's actor-critic code and noticed that some of the neural network's weights are shared ...
0
votes
0answers
11 views

Info regarding unis in United States [on hold]

I really need some inputs here. I am an electrical engineer from India and really interested in the maths behind data science and want to come to US for my MS. I have self taught myself the UG ...
0
votes
3answers
52 views

How can I understand the concept of a noise in machine learning?

In Bishop's book, one of the first examples is shown here Essentially, the data $x$ are randomly generated, and $t$ are generated by running $x$ through a function $\sin(2\pi x)$, then Gaussian ...
0
votes
1answer
24 views

Why Energy in Restricted Boltzmann Machine?

In Restricted Boltzmann Machine (RBM), we define the energy function $E(\mathbf{v}, \mathbf{h}; \, \mathbf{W}, \mathbf{a}, \mathbf{b})$. $\mathbf{v}$ is visible unit $\mathbf{h}$ is hidden unit $\...
0
votes
0answers
17 views

How do the kitchen sink approach used to extract Algorithm's feature?

Hi while reading the article of Predicting Unroll Factors Using Supervised Classification of Saman Amarasinghe and al. they mentioned that they used kitchen sink approach for features extraction. ...
0
votes
0answers
8 views

Impact of C on geometric margin in linear SVM

Will the geometric margin always decrease if we increase $C$ in a linear SVM? When data is linearly separable, that makes sense but I can't really see it when we have nonlinearly separable data.
0
votes
1answer
27 views

What does it mean to “interpret the sigmoid $\sigma(\theta^Tx)$ as a probability”? [duplicate]

In Goodfellow's Deep learning text, it is written Is this way of defining a probability $p(y=1| x;\theta)$ even legal? Recall the definition of a probability given a random variable where $p_X$ is ...
0
votes
0answers
9 views

Conditions for Adaboost to perform well

Under which conditions does the AdaBoost algorithm yield good results even on weak learners (i.e. slightly better than random classifiers)?
0
votes
0answers
14 views

Parallel Bagging in supervised learning

How can we parallelize Bootstrap aggregation, a.k.a Bagging, i.e. train all classifiers at once?
0
votes
0answers
18 views

Why isn't accuracy of binary classification model improving? [duplicate]

I have a data set with a binary response variable, about 30,000 observations of 8 features, some are continuous and some are categorical. This is an imbalanced data set, the ratio of negatives to ...
1
vote
1answer
13 views

Advantages of dual formulation

Why do we solve the dual form of the SVM in practice to obtain a classifier instead of the primal?
0
votes
0answers
12 views

How to compare two sets of time dependent proportions?

I am doing a sentiment analysis task about the people's attitudes towards transportation services in Hong Kong. I collected Tweets near the railway stations and see if there is any difference between ...
1
vote
1answer
50 views

Is the absolute value of the difference a kernel?

In particular is $$ k(x_i,x_j)=|x_i-x_j|, \quad x_i,x_j\in \mathbb{R}$$ a valid kernel?
0
votes
1answer
16 views

Meaning of “card”

The following statement is made in Elements of Statistical Learning: "Our loss function can be represented by a K × K matrix L, where K = card(G)." What does card(G) mean?
0
votes
0answers
6 views

Two FTRL-proximal equations are different and I don't know why

Ad Click Prediction introduces a FTRL-proximal equation as: $$ \mathbf{w_{t+1} } = argmin_{\mathbf{w} }(\mathbf{g_{1:t} }\bullet \mathbf{w}+\frac{1}{2}\sum^{t}_{s=1}{\sigma}_s { {||\mathbf{w}-\mathbf{...
2
votes
1answer
16 views

Which machine learning approach to use for data with very low variability and a small training set?

My goal is to write a program which recognizes the chess position in an image of a digital game. I'm not trying to process actual photos of a game in real life, just images like the own below This ...
0
votes
0answers
21 views

How would one debug a machine learning model that has a bias?

I'm predicting values roughly forming a normal distribution with mean 0. However, my machine learning model tends to predict lower than 0 on average. I didn't run any statistical tests, but it's very ...
0
votes
1answer
26 views

Correcting sample selection bias of binary classifiers

In fraud investigation the number of detected fraud cases can be very small when compared to the total number of cases. This would also apply to rare desease detected in a very small number of people ...
1
vote
0answers
24 views

Advice on ML ideas/models for a data set I have [on hold]

I have a very large marketing data set (300GB in size) and I am wondering what ML models I can apply to it. The dataset consists of transactional data from supermarkets. The type of data I have is the ...
0
votes
1answer
23 views

forget_bias interpretation in tensorflow

In Basic LSTM cell of tensorflow there is an argument named forget_bias. From the documentation of ...
1
vote
1answer
34 views

Out-of bag error in Random Forest

I am trying to code my own, simple version od RandomForest function in R for learning purposes. However I have a hard time understanding the concept of the out-of-bag error. Is it simply done by ...
0
votes
0answers
2 views

GWAS genotype/phenotype datasets for supervised learning model testing [on hold]

I'd like to play around with several ML models and test their predictive power using some good datasets. I need datasets of genotype (a set of SNPs) and phenotype (some trait). If possible, I'd ...
0
votes
1answer
17 views

What is the difference between SSIM and MS-SSIM?

I would like to know what is the difference between SSIM and MS-SSIM? Also, there is a built-in function in Tensorflow for both of them, I am curious to know when should I use SSIM and when MS-SSIM? ...
2
votes
3answers
41 views

Must all supervised algorithms have (complexity) parameters?

I have noticed that all commonly used supervised algorithms (decision tree, logistic regression, random forest, ...) have some (hyper)parameters to tune (otherwise the model may underfit or overfit ...
0
votes
1answer
25 views

Training data has more variables than test data

Given a train and test data that looks like the below: Im wondering if it is necessary to drip the id field in the training data if the id field is present in the test data. Also, if the test data ...
0
votes
0answers
12 views

How to choose the best algorithm to fit neural model [on hold]

Im beginner in machine learning .. I have a problem of classification and i want to fit a neural network model with R and using the function Neuralnet(). but i don't know what is the best algorithm to ...
0
votes
0answers
6 views

Pruning out specific nodes within an rpart tree [on hold]

I have generated a simple tree using the rpart() function (shown below), however I would like to be able to stop the second split at 'Petal.Length < 4.9' before it splits by 'Petal.Width', however ...