Questions tagged [machine-learning]

Machine Learning is a subfield of computer science that draws on elements from algorithmic analysis, computational statistics, mathematics, optimization, etc. It is mainly concerned with the use of data to construct models that have high predictive/forecasting ability. Topics include modeling building, applications, theory, etc.

Filter by
Sorted by
Tagged with
0
votes
0answers
12 views

Guidelines to efficiently train neural networks which have polynomial activations

I am interesting in studying low footprint NN by replacing the activation functions with low-degree polynomial approximations. Doing this, I am fine with slight reduction in accuracy if I the training ...
1
vote
2answers
21 views

How to deal with the difference in the range of Dependent variable in Train and Test data

I am training a XGBoost model for predicting number of applications and the minimum number of applications in training data is 40 and the maximum number of applications is 2000, while in test set ...
0
votes
0answers
51 views

Style Loss in Neural Style Transfer

This is a paragraph from This Book that explains style loss function for Neural Style Transfer. The thing that I dont understand is that from where did they got this: I understood that the Sigma ...
-1
votes
0answers
15 views

Feature Importance and cross Validation in Unsupervised Model

I am working on creating unsupervised machine learning model, and I have some questions. How to get features importance from the dataset? Can I apply cross validation or train test split in ...
0
votes
1answer
19 views

Precision, recall and accuracy metrics significantly different between training/validation and actual predictions

I have two sequential models built with Keras that train on data from a CSV file. This is how they are built ...
2
votes
0answers
57 views

What are available Python libraries for Interpretable ML?

I recently become familiar with Interpretable ML and I found some libraries like LIME. I would be thankful if you can suggest to me some libraries and what are the advantages of each library.
0
votes
0answers
11 views

In Federated Learning what happens when mobile devie is not suitable available?

I've been doing some research about federated learning and came across two questions that I want to clarify. I've been reading and watching videos however no luck and also there aren't questions on ...
0
votes
0answers
9 views

How to deal with time features/seasonality in NYC taxi dataset

I'm using Catboost (and will also construct an LSTM) to predict pickup demand for Queens NYC taxi zones 1 step ahead using data spanning a few months (using resamples of an hour per taxi zone). I ...
0
votes
0answers
5 views

cost function for probability estimation on reduced range

the data: tabular data (low number of columns). the target is binary, available on the train data only. the task: i need to predict probability of a the target to be "safe" the way the ...
1
vote
1answer
27 views

Question About Discriminator of CycleGan

The Discriminator of CycleGan outputs not just a single value to say that the image is real or fake.... But It outputs a grid of numbers (like 8X8 or 7x7), where each number says whether one patch of ...
1
vote
0answers
29 views

Detecting original vs. edited (reposted / recompressed) image

I'm trying to create something to help solve this problem: My goal is that, given two images where one is an edit of the other, produce a system that outputs which one is most likely to be the ...
0
votes
1answer
36 views

Anomaly Detection

I have a problem where I want to identify Vendors with unusual high amount invoices. What would be the best way to identify such invoices? I am trying to use Isolation Forest but having trouble in ...
0
votes
2answers
12 views

How to do node classification without deep learning?

I have a dataset of coordinates with labels, a set of those coordinates (a graph) follows globally the same pattern. ie : I have coordinates of eyes,mouth and nose on thousands of images. A graph can ...
1
vote
1answer
55 views

Need help with prolog program

I am new to prolog and need help on how to write a prolog program. Here is what i am trying to do. I have downloaded the dataset from this link - https://archive.ics.uci.edu/ml/datasets/Blood+...
0
votes
1answer
22 views

What will be the input_shape of tf.keras.layers.Conv3D be for these inputs

I have many videos, and each video is made up of 37 images (there are 37 frames in the whole video). And the dimension of each image is (100, 100, 3).... So the ...
1
vote
1answer
24 views

Classification algorithm that only matches trained examples

I have 10 categorical features and a multi-class target. Training data contains rows where the same 10 categorical features may map to a different target class. What classification algorithm should I ...
0
votes
0answers
83 views

How to do NER predictions with Huggingface BERT transformer

I am trying to do a prediction on a test data set without any labels for an NER problem. Here is some background. I am doing named entity recognition using tensorflow and Keras. I am using huggingface ...
1
vote
0answers
9 views

TensorFlow Poisson error

I am trying to assume that my y variable has a Poisson distribution and I am using TensorFlow to do so. The model I have is as follows: ...
2
votes
1answer
30 views

Best way to model a problem where multiple rows contribute to the result

This is my first question here and I am very computer savvy but a ML novice. I have done lots of learning algo's where the question fits on a single row so I can train the model with a lot of rows and ...
0
votes
1answer
29 views

What would be the best machine learning approach for sets of varying sizes?

I have the following problem: I have two differents sets of labels (extracted using N.E.R) and given a combination of labels of the first set (a,b,c or d) I have a supervised set of best combination ...
0
votes
2answers
36 views

What could be the problem leading to the result that a model can never perfectly overfit?

I tried to fit my model on a small batch of 128 samples for binary classification. The model should be powerful enough as it has hundreds of thousands of parameters. It should be able to overfit to ...
1
vote
1answer
22 views

Finding an appropriate binary classification algorithm for time series data intervals

Maybe someone here has experience in this matter and can point me in the right direction. I want to classify parts of an interval of numerical movement data as either resting or not resting. I have ...
4
votes
1answer
21 views

Does the Bayesian MAP give a probability distribution over unseen data?

I'm working my way through the Bayesian world. So far I've understood that the MLE or the MPA are point estimates, therefore ...
0
votes
0answers
19 views

A/B Test Machine Learning

I'm thinking about a problem where I have data on different A/B tests and which variant won. The features would be a bunch of one-hot encoded functionalities of each page (i.e., blue button, square ...
1
vote
1answer
12 views

Semantic analysis score as input to LSTM model for improving stock price prediction accuracy [closed]

I have created a univariate LSTM model that is predicting value of Open Price based on last 5 years opening price of a particular stock. I'm getting a decent accuracy. Now, I want to do sentiment ...
0
votes
0answers
11 views

Difference between KNN-DTW and DTW Template matching?

Is there a distinction between kNN-DTW and DTW template matching? Essentially DTW template matching computes the DTW for each point in the training set, similar to the KNN-DTW algorithm. Is there a ...
0
votes
0answers
34 views

How do I aggregate cross-validation results for per-sample insights?

I'm trying to do feature engineering for point cloud data with three classes, and after having finished implementing the most obvious and simplest features with somewhat good results I'd like to use ...
0
votes
1answer
21 views

unable to predict by LinearRegression

Should I add csv as text in SO question? There's lot more data. ...
0
votes
0answers
11 views

estimating single or multiple model for Multiple Time Series Forecasting

I am a newbie in the ML field. So please, neglect or better correct, if I am wrong somewhere. I am working on a requirement where details of loading time for each page/component will be given. Now I ...
6
votes
1answer
92 views

What is the best way (cheapest / fastest option) to train an model on massive dataset (400GB+, 100m rows x 200 columns)?

I have a 400GB data set that I want to train a model on. What is the cheapest method to train this model? The options I can think of so far are: AWS instance with massive RAM and train CPU (slow, but ...
0
votes
1answer
15 views

How do Classification Algorithms such as Catboost and Random Forest parse test data?

I would like to know how classification works with the algorithms listed above. My specific question is this, say I have a high signal continuous feature which has a certain distribution and I train a ...
0
votes
1answer
16 views

Steps to fit a Machine learning model for prediction of up and down market movement

I have around 5 years of data of an index containing many features on a daily basis. I want to classify whether the index will move up or down the next trading day (up or down movement is determined ...
0
votes
0answers
10 views

DTW and kNN-DTW time complexity

I have implemented KNN using a custom DTW metric with sci-kit learn and as shown below: ...
0
votes
0answers
9 views

Learning a and predicting workflow for a certain goal

I am trying to come up with a strategy which could learn a workflow for various goals and then based on some input goal, predict the workflow which could fulfil the goal. Goals are achieved by ...
0
votes
1answer
13 views

Finding best match/score between 2 datasets

I am looking for a potential matching algorithm to apply to 2 datasets (DS1,DS2), that would provide a score for all DS1 x DS2. To exemplifies the problem: imagine a pool of job seekers are looking ...
1
vote
0answers
12 views

How to take the keywords from the given dataset to train GPT-2 based chatbot?

I am working with a dataset that contains Questions on various Events conducted by a college and the corresponding answers for the queries. I am using this dataset to train a GPT-2 355M model to ...
3
votes
2answers
31 views

Understanding Weighted learning in Ensemble Classifiers

I'm currently studying Boosting techniques in Machine Learning and I happened to understand that in Algorithms like Adaboost, each of the training samples is given a weight depending on whether it was ...
0
votes
0answers
15 views

AI with metadata and timeseries inputs

In data science you sometimes encounter a scenario where you have meta data on a given process and the process data itself. For example you have a mechanical component that is tested over time. So you ...
0
votes
0answers
18 views

Can I get a global attribution when using Shapley values?

I'm using a shap KernelExplainer to interprete my model and I'd like to display a global attribution for each feature. The idea is to represent, in a numerical way, the plot. What would be the best ...
1
vote
1answer
35 views

Is feature importance from classification a good way to select features for clustering?

I have a large data set with many features (70). By doing preprocessing (removing features with too many missing values and those that are not correlated with the binary target variable) I have ...
0
votes
1answer
12 views

Is there a difference between Vectorization and Featurization?

I have come across articles that mention Featurization and Vectorization interchangeably. Is there a minute difference between each other or are they exactly referring to the same thing?
1
vote
1answer
48 views

Unsupervised Text Classification with Python: Kmeans

I am working on a project to build a text classifier of questions being asked. There are no labels provided in my data so I have chosen to go with an unsupervised approach. This solution needs to read ...
0
votes
0answers
8 views

Getting low/very uncalibrated predictions on new data for regression using xgbtree method in train() function in R's caret package

I recently tried creating a regression model (imagine a model with the target variable being an integer with values 10-110) using xgboost (method = 'xgbTree') with caret. The model trains successfully,...
0
votes
0answers
9 views

Normalization in Neural Networks Regression in MATLAB

I have 20 samples for a regression fitting purpose in Neural Network Toolbox (nnstart, nftool) in MATLAB . I have 3 inputs of 20 samples each (3 X 20 ) and 1 output (3 X 20, as the output number is ...
0
votes
0answers
13 views

Is it possible to use Memory Augmented Neural Network for regression?

Now I am working on stock price prediction using Machine Learning. I have tried different methods (ARMA, LSTM, GRU). Now I would like to try MANN (Memory Augmented Neural Network). I have tried to ...
1
vote
1answer
28 views

Classification using texts as features

I want to build a classification model to match customers and products. I have a description of each product, and a description of each customer, and the label : ...
-1
votes
0answers
5 views

TypeError: fit_generator() got multiple values for argument 'steps_per_epoch' [migrated]

I am trying to train keras model. Below is the function for train model. ...
1
vote
1answer
27 views

Adjusting imbalance in classification problem reduce precision, accuracy but increase recall

I've learned that adjusting imbalanced data when training a CNN affects model performance which got me thinking "what about in ML?" so I've done some testing on my own, you can check it out ...
0
votes
0answers
16 views

Understanding Standard Error of Regression Coeficients (ISLR)

During my reading of Introduction To Statistical Learning, I reached this part and I'm facing a very hard time trying to understand what is being said: This highlighted words are telling that this is ...
0
votes
1answer
65 views

Class token in ViT and BERT

I'm trying to understand the architecture of the ViT Paper, and noticed they use a CLASS token like in BERT. To the best of my understanding this token is used to gather knowledge of the entire class, ...