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 automatically improve with experience."

1
vote
0answers
3 views

Wavenet joint probability

As presented in the first article of Google Wavenet (https://arxiv.org/pdf/1609.03499.pdf) the model can approximate the joint probability of the whole sequence (raw audio waveform) using the chain ...
0
votes
0answers
3 views

Dataset image size and inference speed

Does training a pre-trained model on a the same dataset but with sizes scaled down (e.g., by 70%) improve inference speed? More generally, does training a CNN on smaller images improve inference speed?...
2
votes
1answer
17 views

Pytorch: How to create an update rule the doesn't come from derivatives?

I want to implement the following algorithm, taken from this book, section 13.6: Here, the neural networks' outputs are $V(S, w)$ and $\pi(A|S,\theta)$, parameterized by $w$ and $\theta$ respectively....
1
vote
0answers
12 views

Is a good shuffle random state for training data really good for the model?

I'm using keras to train a binary classifier neural network. To shuffle the training data I am using shuffle function from scikit-learn. I observe that for some shuffle_random_state (seed for ...
0
votes
0answers
6 views

Approach fpr extracting/cropping features images using deeplearning and no annotations

Let's say I want to have a bunch of images of hats from videos. How would I priniciple build something that would learn to recognize, and crop or bound box hats? I heard you need a dataset with ...
1
vote
1answer
10 views

Layman's description of PDF and CDF

Can anyone please explain PDF and CDF in simple words. (Please don't define it from wiki.)
3
votes
2answers
687 views

Data scaling before or after PCA

I have seen senior data scientists doing data scaling either before or after applying PCA. What is more right to do and why?
0
votes
1answer
14 views

What does it mean for an activation function to be “saturated/non-saturated”?

For context, in this paper Several RNN variants such as the long short-term memory (LSTM) [10, 18] and the gated recurrent unit (GRU) [5] have been proposed to address the gradient problems. ...
3
votes
0answers
17 views

Scaling does not speed up the SVM model

I tried to standardize the training data with samples of 629,145 rows and 24 features: ...
2
votes
0answers
9 views

Should one normalize the frequency values when feeding it as an input to machine learning model?

Consider an unsupervised data. The data is in the form of a csv file( I am using pandas dataframe for this). Its a web page data at different time steps and the way I am converting data to be fed to ...
2
votes
1answer
23 views

Find best machine learning for predicting category of products

I have a dataframe that contains product and in this dataframe I have some features like: brand, cat1, cat2, ...
1
vote
0answers
27 views

Stacking with missing predictions from models [on hold]

There are several models A, B, ..., Z. These models may not give a prediction for any of entities from id1, id2, id3, .., idn. What approaches will be more suitable for stacking in these situations? ...
1
vote
0answers
11 views

How much data would be remain unaffected? [on hold]

our data set has missing values. Further examination tells you that they are spread along 1.5 standard deviation from the median with distribution mean = 0 & variance = 5. How much data would ...
1
vote
2answers
39 views

Tattoo Image Recognition - Should I Crop Training Data Background

I am trying to train a neural network to detect objects within a tattoo. I couldn't find any existing labeled dataset so I need to manually create and label my own. I only understand the basics of ...
2
votes
1answer
19 views

Data splitting for a binary classification model

I'm trying to build a binary classification model that will tell who's going to buy the product and who's not. I've heard that splitting a dataset into two different subsets is a common way when you ...
2
votes
1answer
22 views

Many things behave differently in high dimensional space

It turns out that many things behave very differently in high dimensional space. The below paragraph is picked from a book. I need extra help to understand. The book says, if you pick a random ...
1
vote
1answer
13 views

Product classification in hierarchical categories based on multiple parameters and non-standard descriptions

I want to start a machine learning project in my company and a really big pain for spend analysts is to classify the products that buyers order for maintenance, tooling, raw material and such, as the ...
1
vote
2answers
670 views

use machine learning to predict a next day of visit for customer

I have a problem a need your suggestion , I am working in a retail data , and want to predict the behavior of the customer , the data contains information about the customer who visits the shopping ...
1
vote
2answers
19 views

Naive Bayes Classifier

Could someone please explain to me how and why can we go from equation $4.3$ to equation $4.4$: $$\hat{c}= \arg\max_{c \in \mathcal{C}}P(c|d) = \arg\max_{c \in \mathcal{C}}\frac{P(d|c)P(c)}{P(d)}\tag{...
1
vote
0answers
11 views

How can positional encodings including a sine operation be linearly transformable for any offset?

In the paper "Attention is all you need" the authors add a positional encoding to each token in the sequence (section 3.5). The following encoding is chosen: $ PE(pos, 2dim) = sin(pos / 10000 ^ {2dim/...
1
vote
0answers
11 views

Reasons why training error can go up after more training?

In the context of deep-learning, I understand why the test or validation error can go up with more training: this is the result of overfitting. I also can think of one reason why even the training ...
2
votes
1answer
22 views

Multivariate Time Series Binary Classification

I have continuous (time series) data. This data is multivariate. Each feature can be represented as time series (they are all calculated on daily basis). Here is an example. ...
2
votes
2answers
70 views

Why Sckit's fit_transform causes a huge drop in accuracy and all other evaluation metrics?

Trying to use sc.fit_transform(X), I get a huge drop in accuracy on the same model. Without scaling the values of my dataset, I get accuracy values of 80 - 82%. ...
3
votes
1answer
21 views

What is the significance of orthogonality in regression

Can somebody please explain intuitively why the variables need to be orthogonal to each other? Does orthogonality imply independence? When the variables are independent then we get an estimate using ...
3
votes
1answer
28 views

Is shuffling training data beneficial for machine learning?

I was curious to know if shuffling ML training data is beneficial to better results? Sorry not a lot of wisdom here, but I have been reading a post from pythonprogramming.net for this topic. I ...
2
votes
1answer
8 views

How to Normalise features for small datasets?

I am working with a small dataset ( N = 50 ). I would like to normalise my input features. I am facing the following issues: Because of the small size of the dataset the range of training input ...
2
votes
2answers
17 views

What does a negative coefficient of determination mean for evaluating ridge regression?

Judging by the negative result being displayed from my ridge.score() I am guessing that I am doing something wrong. Maybe someone could point me in the right direction? ...
1
vote
1answer
28 views

Machine learning algorithm that uses the Pearson or Spearman correlation?

I've come across linear and multiple regression, SVM, random forests. Does any know of a machine learning algorithm that uses the Pearson correlation or Spearman correlation? Best, Dave
1
vote
1answer
19 views

How to measure variable contribution to an observation in a non-linear model?

Based on my model, if I decline someone due to their score, it should be able to provide some reasoning as to which variables mainly contributed to the decision to decline. Typically in Logistic ...
1
vote
0answers
14 views

Model the predictive relationship between images

Hello fellow machine learners, We have numerous pairs of 64 x 64 (or other dimensionality) images (maps). In each pair, the first image demonstrates a physical parameter, e.g. wind speed, at each ...
1
vote
0answers
8 views

What is the interpretation of the expectation notation in the GAN formulation?

I'm confused about the expectation notation in the context of GAN loss functions. The GAN loss for the discriminator is binary cross-entropy. ie: is this real or not. real = $D(x)$ (ie: give ...
3
votes
1answer
46 views

Linear optimization problem of $argmin$

Consider a vector $a \in R^n$. I want to know how I can find analytically the solution of the following optimization problem: $x^* = argmin_{x \in R^n} f(x)$, where $f(x) = ||x-a||_{2}^2 + \lambda ...
1
vote
0answers
22 views

Simulate Biased dataset Python [on hold]

I am trying to show that bias does not go away with larger sample sizes and show plots using python in samples of 100 1000 100000. I'm not sure how to approach. It's for a school example
-1
votes
2answers
464 views

How is the generator code works in a GAN?

I am going throught GAN for image generation and I am using this article for reference. The author is creating a generator model which does this. and the generator model code is ...
0
votes
0answers
6 views

Difference between Long Short-Term Memory model and Self Exciting Point Process model

I've been reading about Hawkes process (https://arxiv.org/pdf/1708.06401.pdf) and how it is used to predict future events based on frequency of similar events in the past and it kind of seems similar ...
0
votes
2answers
19 views

Time of trainig vs time of prediction, which one is used during classification algorithms comparison?

I need to use many algorithms for making a binary classification, such as Logistic regression, SVM, XGBoost, CatBoost, ... I get an interesting improvement but All of those algorithms (except LR) take ...
0
votes
0answers
15 views

Text classification problem [on hold]

Am asked to extract tenders titles in a specific work-field (expl: oil sector) from the web , am really beginner in NLP , what steps and methods do i have to use ?
1
vote
2answers
25 views

How to deal with overestimation of small values and underestimation of high values in XGBoost?

I'm running XGBoost to predict prices on a cars dataset, I was wondering what alternatives are there for this kind of problem ...
0
votes
2answers
17 views

Regression using gradiant boosting - smoother predictions

I have practical machine learning problem. I have trained a LightGBM model to predict house prices. Compared with other models I have tried, the loss (RMSE) is quite low and overall I'm quite happy ...
2
votes
1answer
1k views

Apply SVM on LDA in python

hope someone kindly put time here, my approach is like this: TFIDF -> LDA -> SVM I am using LDA to extract topics. I want to do topic modelling and use the topics as features to do document ...
3
votes
1answer
49 views

Does it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?

this is my first machine learning project and actually also my first question here. I am a novice to machine learning with a background in theoretical physics. I want to use a CNN to detect scratches ...
2
votes
0answers
10 views

Sequence to sequence LSTM is “slow” to observe changes. Can this be improved?

I have some multivariate time series, and I'm trying to teach an LSTM with simulated data what is good and what is bad, so the input is a timeseries with a label for every timestep, i.e. [1,1,1,1,1,1,...
1
vote
1answer
13 views

Doubt regarding the number of weights in 2 layer neural network

Considering a hypothetical scenario , where we have 10 input layers, and 5 output layers. How many weights are there in the neural network? If this is implemented in pytorch, the answer will be 50. ...
1
vote
0answers
11 views

Training anomaly detection on text string [on hold]

I have text string stored in a column, resulting after pre-processing of web traffic data. Now I want to apply anomaly detection on it and for that purpose I applied ...
19
votes
4answers
480 views

What statistical model should I use to analyze the likelihood that a single event influenced longitudinal data

I am trying to find a formula, method, or model to use to analyze the likelihood that a specific event influenced some longitudinal data. I am having difficultly figuring out what to search for on ...
3
votes
0answers
29 views

Why I am getting prediction score 1 i.e. 100%

I am reading few parameters and trying to predict target value using Linear regression and GB. Surpicingly I am getting score = 1 on test data. How come? Can anyone tell me whats wrong with this code? ...
2
votes
1answer
35 views

ML algorithm with fixed number of inputs and variable number of outputs

I am trying to solve the following problem: Let's say I have a chess position: I encode each square as one-hot encoded vector of length 13 index 0 for empty square index 1 for white pawn index 2 ...
2
votes
1answer
5k views

Dimension of weight matrix in neural network

Why would the dimension of $w^{[2]}$ be $(n^{[2]}, n^{[1]})$ ? This is a simple linear equation, $z^{[n]}= W^{[n]}a^{[n-1]} + b^{[n]}$ There seems to be an error in the screenshot. the weight, $W$ ...
5
votes
0answers
31 views

How to deal with possible data leakage in time series data?

I have historical consumer data who have taken out a loan at some point in time. The task is to predict if a consumer will default when requesting a loan. My issue is that for some customer in the ...
-1
votes
0answers
30 views

Machine learning [on hold]

Please i am stuck using machine learning for find association between data just I have one column input vector and one output target i want to match the values from vector a to b (There is not ...