Questions tagged [machine-learning]

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

Filter by
Sorted by
Tagged with
-1
votes
0answers
7 views

Synonymous word suggestion Model

I want create a machine Learning model which will suggest synonyms of the words of a sentence which can adapt to user usage. I am targeting Continuous Learning Model for this purpose. I have already ...
2
votes
0answers
6 views

Geometric classification models

In class we have been presented with a Geometric classification model such that the goal is to construct a linear decision boundary $\bf{w} \cdot \bf{x} = t$; where $\bf{w}$ is the vector from the ...
-2
votes
0answers
15 views

How can I improve the accuracy of the following classifier algorithim?

Currently the classifier works as follow: I have a training data set and a testing data set, the classifier trains N ID3 tree, as follows: suppose the training data set is of size m, then I sample p(...
1
vote
0answers
10 views

Encoding Data for ML Modeling with Key Value Pair

Apologies in advance for the poor title. I didn't know exactly how to phrase what I want in a succinct manner so hopefully I can elaborate a bit more. I have a dataset where I have customer_id, ...
2
votes
0answers
7 views

References/tutorials about data mining and machine learning

I am learning data analytics and I wonder if there are some good references and tutorials about machine learning, data analytics and data mining? What I'm searching for is an understandable reference/...
1
vote
0answers
9 views

Alternatives to GCP / AWS / Azure

Can anyone recommend an alternative to the big 3 cloud computing alternatives? I know they're the best but I found them overly complicated because they cater to massive enterprises. The amount of set ...
1
vote
0answers
15 views

Single layer multiple input neural network?

I am implementing single layer neural network using stochastic gradient descent. When I train the model for single input it gives the answer correctly. Now when I use the second input to update my ...
1
vote
1answer
10 views

Which metric to use for evaluating a rating system

I have a system which gives a star rating of the quality of work(on scale of 1-5, 1 being extremely poor and 5 being exceptionally good). An expert labelled a test set with their ratings of quality of ...
2
votes
0answers
15 views

Big Data clustering

I've got some big datasets of images (few million each) and I would like to cluster them according to images' visual similarities. I've extracted a feature vector for each image; the space of feature ...
1
vote
0answers
19 views

Data\Feature Leakage - feature too close to target?

In General: I have a problem in the following method: Output: binary. built from multiple binary scenarios. Input: multiple features + features very close to the scenario. For Example: Output: ...
1
vote
0answers
6 views

Ensemble of different reservoirs (echo state networks)

Suppose I want to do reservoir computing to classify the input to the proper category (e.g. recognizing a handwritten letter). Ideally, after training a single reservoir and testing it, there would be ...
1
vote
0answers
20 views

Unexpectedly long computation times with nested cross validation

Hello StackExchange community, I am trying to apply Nested Cross Validation on a pipeline to get a reliable estimate of the generalization error of my model. The pipeline includes two steps: Scaling ...
0
votes
0answers
9 views

Incremental learning for Gradient Boosting Classifier & Random Forest Clssifier

I have been trying to get a method to incrementally learn additional data which my model for both random forest and gbm to consume as and when we get it. I can of course retrain the model everytime I ...
1
vote
0answers
29 views

Best algorithm/model to establish relevance between events utilizing mixed data type (Tags, Time, x_coordinate, y_coordinate)?

I'm building a relevance ranking system for incidents occurrence and prevention. My goal is to use four attributes to establish relevance: tag (About 500 tags), x_coordinate, y_coordinate and time. ...
2
votes
0answers
31 views

flexibility vs complexity vs number of predictors in machine learning

I'm new to machine learning so am quite confused with the above concepts. It seems to me both flexibility and complexity measures how well the model fit the data (in terms of the curvy-ness), so what'...
0
votes
1answer
23 views

When to use cross-validation?

Cross-validation Hi, I'm deploying machine learning models in my MSc thesis using Weka. I have noticed that when I use 10-fold cross-validation in the training dataset I get low evaluation metrics ...
1
vote
0answers
12 views

Handling missing data - secondary driver characteristics in insurance data

I have an insurance dataset which includes an indicator that indicates whether the policy insures a secondary driver, and the secondary driver's age/sex. Problem is most policies do not have secondary ...
2
votes
0answers
29 views

ARIMA training super slow

I am fitting ARIMA model (from statsmodels) on 20 000 elements dataset on a 24 CPU 200+GB RAM cloud server for over 24 hours now. It loads all the CPU's. But It takes so long... Is it how it works or ...
1
vote
0answers
16 views

Should I create thousands of models (one per user) or a single one?

I have application data for a mobile app and I have thousands of users: Should I create one ML model for each user or a single ML model for the entire application? Here is a cartoonish version of my ...
1
vote
1answer
19 views

How to improve performance of Tensorflow's CNN example? [closed]

In the example in this link: https://www.tensorflow.org/tutorials/images/cnn, the performance is over 70%, how can I improve it? What parameters do I need to tweak? Thanks.
1
vote
1answer
18 views

Bert and SVM classification

I'm trying to understand the concepts in the title and how they fit into the task of binary classification. According to my understanding so far, you can encode text using various feature-extraction ...
1
vote
0answers
9 views

Liveness Detection System - Suggestions

I am trying to build a liveness detection system but till now I haven't been able to generate any significant results. I read the article by pyimagesearch this on the same topic but no luck. Tried ...
1
vote
0answers
24 views

Shared weights for features in Conditional Random Field

I am going through two materials regarding Conditional Random Fields. The first one is this (referred to as [1]) material by Charles Sutton and Andrew McCallum and the second one is this (referred to ...
-1
votes
0answers
12 views

Statistics : CART ALGORITHM [closed]

I tried to solve this question but couldn't solve it! Please Help Q) Try to manually compute the first split point that the CART algorithm would do on the following dataset, use x as feature. x: 1 2 7....
0
votes
1answer
19 views

How do the linear layers in the attention mechanism work?

I think I now the answer to my question but I dont really get confirmation. When taking a look at the multi-head-attention block as presented in "Attention Is All You Need" we can see that ...
0
votes
0answers
12 views

Understanding the training of R-CNN architecture, why is SVM necessary?

In the R-CNN paper, when referring to the training of CNN extraction module, the authors say: "Aside from replacing the CNN’s ImageNetspecific 1000-way classification layer with a randomly ...
0
votes
0answers
22 views

Any insights on gradient boosting algorithms for classification task with large class number?

Recently I have been learning Gradient Boosting (GB) on multi-class classification. I searched Google Scholar for a while and found one paper on multi-class classification using GB 1. However, little ...
1
vote
0answers
19 views

Linear transformations making independent features dependent

I read about features and some relevant topics recently. I ran into an easy but very advanced question: Why can two independent features become dependent after applying a linear transformation? I ...
1
vote
1answer
20 views

Test set larger than train set [closed]

There is a two class dataset with 1121 values in total, having 230 from same class and 891 from the other class. The training set is choosen as 230+230=460 from both classes and the test set as the ...
0
votes
0answers
9 views

Denoising Prior to Image Classification

From what I have read, Denoising during preprocessing for image classification tasks seems to be a bit controversial. While on one hand it might improve classification accuracy, the computational ...
1
vote
1answer
11 views

Clustering using both text and numerical features

I have a dataset that contains 2 types of features, one is generated from doc2vec and one is numerical feature. I would like to perform clustering analysis on them. However, due to the size of doc2vec ...
2
votes
0answers
22 views

h2o much faster than neuralnet (in R)

I’m a novice to machine learning. I've been trying out different neural network implementations in R, including the neuralnet package and the deeplearning function of the h2o package. For neuralnet, ...
0
votes
1answer
20 views

Which algorithm should I choose and why?

My friend was reading a textbook and had this question: Suppose that you observe $(X_1,Y_1),...,(X_{100}Y_{100})$, which you assume to be i.i.d. copies of a random pair $(X,Y)$ taking values in $\...
2
votes
0answers
21 views

Recommended ways of building data science teams

I'm not sure if this questions belongs to this place. But I will be very interested in knowing the answer. I work for the Public Administration in Spain. We want to build a data science team, and in ...
1
vote
1answer
13 views

Is it possible to make use of the CPU RAM, if i'm running of of VRAM, in tensorflow?

I want to train a model running on tensorflow. I have a GPU but it only has 6gb of VRAM. So i was wondering if it is possible to use some of the CPU's RAM to offload the GPU? I know it will be much ...
0
votes
0answers
26 views

How to merge multiple filters of a layer to a single filter in convolutional neural network?

In a convolutional neural network (CNN), the layer weights are learnt such that they extract meaningful features from the data. For each layer, can we merge multiple filters into a single filter after ...
4
votes
3answers
361 views

Why fitting/training a model can be considered as learning? [closed]

I was looking around and I can't find a good answer, I just want to know why it can be considered as learning and is not just "calibration" or "parametrization". I feel the word &...
4
votes
2answers
32 views

Machine Learning with intended missing values

I have a dataset relating to humans completing reviews, the target variable is whether the review decision is correct / incorrect and one of my features is a trailing 4 week accuracy score for the ...
0
votes
0answers
9 views

Is it ever advantageous to perform regression on integer-typed label?

Right now, my program's type-checking prevents regression analysis from running on integer labels. It assumes ints are for ordinal/ OHE classification. I just ran a test and verified that it is in ...
0
votes
0answers
20 views

Weighting of features in Recommender Systems

I'm new to Recommender Systems, and wanted to figure some things out in order to make the best possible Content Ranking System. I want to make a ranking of all the content (and content providers) ...
0
votes
1answer
13 views

What layer to consider for embeddings when building a encoder-encoder model?

I am currently building a encoder-encoder based model with cosine loss function. The dataset is supervised learning. Here's a basic encoder, ...
0
votes
0answers
11 views

Any tips on transfer learning for a regression problem using 4D images as input?

I developed a CNN based on EfficientNet in order to predict the weight of piles of some materials in an image (the labels are the weights in kg and the input is RGBD tensors of the object). I have two ...
1
vote
0answers
16 views

Machine translator giving only on character as output for all the words

I had trained a machine translation model using 1.4 million examples.( hindi to english ). strangely the loss plateaus at the same point 0.8301 and while trying the inference the output is always the ...
1
vote
1answer
33 views

Keras 1D CNN always predicts the same result even if accuracy is high on training set

The validation accuracy of my 1D CNN is stuck on 0.5 and that's because I'm always getting the same prediction out of a balanced data set. At the same time my training accuracy keeps increasing and ...
3
votes
1answer
45 views

At what stage are ROC curves used when building machine learning model?

When developing a machine learning model, at what stage are ROC curve with AUC used? Typically I have three data sets train - ...
2
votes
1answer
21 views

Cannot understand feature extraction

I'm following an AI course and we've just entered the deep learning chapter. Speaking about the difference between classic machine learning models and deep learning, it turns out one of the most ...
1
vote
1answer
21 views

Creating features from raw accelerometer data

I have a dataset containing raw 3-axis accelerometer data collected from a users lower leg and I want to create a classification model (as simple as possible) that detects if the user is sat down or ...
0
votes
0answers
15 views

What is explicit fitness sharing in NEAT?

I cannot understand what is explicit fitness sharing. Could someone explain it?
1
vote
1answer
32 views

How to impute missing value in Test Set using a custom Imputer created on training dataset

I am working on a toy project to predict claims. One of the input features has null values on which I have applied a custom imputation technique. Under this technique, I replaced missing values with ...
-1
votes
0answers
26 views

What does 'specie' mean in the Neat Algorithm [closed]

What does 'specie' mean in the Neat Algorithm? NEAT Algorithm Papers: Here

1
2 3 4 5
172