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
2 views

Keras very low accuracy, saturate after few epochs while training

I am very new to the data science domain and directly jumped to TensorFlow models. I've worked on examples provided on the website before. My first time doing any project using it. I am building a ...
0
votes
0answers
6 views

Best Model for Multi-label image classification

Usually using CNN architecture with a Sigmoid function as an activation function in the last layer and using binary cross entropy can be used to output a probability for each class. However, the ...
2
votes
0answers
15 views

Find VC dimension

I'm studying theoretical machine learning at university, and I have this problem in textbook, that I have no Idea how to start. In space $X=R^2$ are given two models $H_1$ (rectangle with sides ...
2
votes
1answer
17 views

Recurrent Neural Network (RNN) Vanishing gradient problem - Why does it affect earlier timesteps more?

I understand the concept of backpropagation in standard neural networks and backpropagation through time with RNNs, why this causes exponentially smaller gradients at earlier time steps and most of ...
0
votes
0answers
20 views

Getting a neural network to approximate x^2

I don't get why it is so hard to get my neural network to learn such a simple function. I've tried all sorts of combinations of layer numbers, number of neurons but it doesn't seem to want to learn. ...
0
votes
1answer
12 views

How to add 'other' as one group to clustering algorithm inference pipeline

I have few clustering algorithms tuned having 5 cluster. I want 6th cluster if new data does not belong initial 5 cluster fall in 6th cluster. 6th cluster [ say other category] consist of all data ...
-1
votes
1answer
26 views

How to get started with Data Science? [closed]

I'm very interested by Data Science and Machine learning, but don't know where begin my learning. I'm really confused in lot of information and tutorials? What is the basic of basics ? By what point ...
0
votes
1answer
15 views

Is there a way to perform edit distance (Levenshtein) character by character between two string columns? [closed]

I have two datasets: dataset1 & dataset2, which have a common column called SAX which is a string object. ...
0
votes
0answers
7 views

Can ReliefF implicitly predict non-linear correlation between features and targets?

Let's assume that we have a collection of instances with their features and already labelled and train them for Relief/ReliefF classifier. If the targets themselves have parameters that defined ...
0
votes
0answers
20 views

Using variance Threshold removes all my features (clustering)

I have 100+ features for clustering. I am unfamiliar with unsupervised tehcniques for clustering. I have heard of variance threshold. However the features i have used have low variance.. e.g. some ...
0
votes
1answer
28 views

Should I make single machine learning model for predicting price of house or 6 different models, given 6 datasets for different cities?

I am currently working on "Housing Prices in Metropolitan Areas of India" (kaggle dataset), with 6 different csv files for 6 different cities. All have same columns (40). Working on a real ...
-1
votes
0answers
14 views

How to predict multiple related values with one value [closed]

first of all i have to say that i am a complete beginner in machine learning. For an architecture project i would like to predict multiple values with only one Value. For example: I would like to ...
1
vote
1answer
29 views

Can we fine-tune a model on the same dataset which it is pretrained on?

So I was reading this paper (about a use case of pretraining then self-training) which got me thinking - suppose I pre-train a model on a particular dataset, then fine-tune it again on the same ...
-3
votes
0answers
21 views

which machine learning algorithm would give high accuracy in predicting the movie rating [closed]

I want to predict the movie rating with the help of voted users, profit, FB likes, etc. which algorithm would the best to predict it
0
votes
3answers
51 views

Removing correlation between independent variables

If there are two continuous independent variables that show a high amount of correlation between them, can we remove this correlation by multiplying or dividing the values of one of the variables with ...
0
votes
0answers
7 views

How do PoseNet identifies the key points of human pose estimation?

PoseNet is a deep learning TensorFlow model that allows you to estimate and track human poses by detecting body parts such as elbows, hips, wrists, knees, and ankles , It uses either MobileNet or ...
0
votes
0answers
12 views

Which Machine learning Algorithm would work best in predicting particle size distribution (PSD)?

Im a beginner with machine learning and data science. i am working on a project where i have to work with an algorithm/ machine learning model that would predict the particle size distribution ( a ...
-1
votes
0answers
14 views

Find the best data transformation, automatically, before looking for the best algorithm

Imagine a binary classification problem with 10 features. We draw a scatter plot for each pair of features and we color by class. In the end, our observation didn't show any clear separation between ...
0
votes
1answer
21 views

Training a neural network with TWO possible correct outputs for one input

I have a system as a black box that has two correct outputs for a single input sample. now I want to train a neural network to generate at least one of the correct outputs for that input sample. what ...
-1
votes
1answer
11 views
0
votes
2answers
28 views

Is it recommended to compute the average of metrics for classification?

For computing the performance metrics of the models used for classification. Is it recommended to repeat the experiments many times (for example 10 times) and compute the average? In my case, I used ...
1
vote
1answer
56 views

How to make our own environments for reinforcement learning?

How can we make our own environments for reinforcement learning? I have a heavy doubt that a game engine is used.. And if a game engine is used, which game engine is used that can be downloaded for ...
0
votes
0answers
13 views

Transfer Deep Learning from one aerial imagery datset to many others

I am new to Deep Learning but have been able to use RasterVision successfully to predict building footprints within a set of aerial imagery. This aerial imagery data set is for a province of New ...
0
votes
0answers
15 views

BinaryEncoder on test set causes different feature count than on training set

I am using a BinaryEncoder from the category_encoders package. I used it to encode a feature in my training set: 30k samples, 1170 unique categories for the feature in question, that resulted in 12 ...
0
votes
0answers
23 views

VC dimensionality exercise

I'm studying theoretical machine learning at university, and I would like to know how to solve this VCdim inequality ? I managed to understand the VCdim exercises but this seems too complex for my ...
0
votes
1answer
18 views

Which Algorithm did OpenAI used to create a hide and seek playing Agent?

I just saw this video on youtube: https://www.youtube.com/watch?v=kopoLzvh5jY&t=9s Which Algorithm did OpenAI used to create a hide and seek playing Agent? Was it Genetic Algorithm or Policy ...
0
votes
0answers
15 views

How can i decide on which features to use for clustering?

I am clustering on a dataset where each row is a customer and each column is a feature. I have 200 features, this seems like alot for clustering. I plan to experiment with a variety of clustering ...
0
votes
0answers
16 views

How to classify all words in a sentence with a context?

I have the names of the companies (in Russian). The name can contain abbreviations, words with capital letters, words with lowercase letters, and mixed words. The model is trained according to the ...
0
votes
0answers
13 views

Create a framework to test effectiveness

I’m going to make up the use case here. Let’s say I’m testing an equipment with software. I can configure the test software to run for any duration - 2 minutes or 8 hours. Hypothesis is that the ...
0
votes
1answer
44 views

Actor Network Target Value in A2C Reinforcement Learning

In DQN, we use; $Target = r+\gamma v(s')$ equation to train (fit) our network. It is easy to understand since we use the $Target$ value as the dependent variable like we do in supervised learning. I....
0
votes
1answer
16 views

Understanding clusters after applying PCA then K-means

I have a dataset grouped by customer level, and the rows are sum_mexico, sum_uk, ... etc to indicate if the customer has spent money at stores in those countries..similarily counts for these as well. ...
0
votes
0answers
15 views

How to filter data samples which do not improve classifier?

I have a text dataset with noisy labels and an unbalanced shape. There are various ways to find features which do not drive improvement in some metric, and help to prune those from the pipeline. I ...
0
votes
0answers
7 views

How to create a pipeline out of this kaggle notebook and automate it with Luigi?

I am new to ML and I was wondering if there's anyway to convert this notebook into an ML pipeline and automate it with a tool like luigi? https://www.kaggle.com/olivierg13/wine-ratings-analysis-w-...
0
votes
0answers
23 views

Neural net performance using rmse

I am trying to build a NN which can predict exchange values. I am quite new to R and NN and I don't quite understand how I could improve the performance metrics of the neural network. I have tried ...
0
votes
1answer
26 views

VC dimension for Gaussian Process Regression [closed]

In neural networks, the VC dimension $d_{VC}$ equals approximately the number of parameters (weights) of the network. The rule of thump for good generalization is then $N \geq 10 d_{VC} \approx 10 * (\...
0
votes
0answers
7 views

How can interparet shap.summary_plot and its gray color concerning outliers/anomaly?

I inspired by this notebook, and I'm experimenting IsolationForest algorithm using scikit-learn==0.22.2.post1 for anomaly ...
-1
votes
0answers
14 views

Design of loss function for unsupervised learning neural network

Input is a string: get filename (e.x., get file.txt get hello.txt) output: predict a number between 1 to 15 Property need to be translated into loss function: define in the loss function that, even if ...
-1
votes
0answers
10 views

Grid Search returns only NaNs. Is it my data? Is it my application? [closed]

I am attempting to optimize parameters using GridSearchCV . However, when I do so the gridsearch appears to run, then returns all NaN values. I read somewhere that this means the model is failing to ...
0
votes
0answers
8 views

Reinforcement Learning - Ray[RLLib] Supported models are predicting less than gym.spaces.Box - low values and throwing error [closed]

I am new to ray - reinforcement learning. I am trying to build a ray-ppo algorithm which will predict cloud hardware capacity required for an org in terms of compute, memory. My reward is a simple ...
0
votes
1answer
15 views

Classification Based Collaborative Filtering Model

I was going through algorithms for collaborative filtering-based prediction. Most of the places, I read about using matrix factorization based on ratings of the likeness of the user. But for my use ...
1
vote
1answer
24 views

Why are convolutions still used in some Transformer networks for speech enhancement?

So I’ve read in Attention is All You Need that Transformers remove the need for recurrence and convolutions entirely. However, I’ve seen some TNNs (such as SepFormer, DPTNet, and TSTNN) that still ...
1
vote
3answers
44 views

Building a multiclass classifier that can handle classes it has never seen?

I am given a dataset that has free-form text and a category associated with it. There are 100 different categories and 3000 records for each category. The goal is build a multiclass classification ...
0
votes
0answers
22 views

Can data science be used to detect fileless malware cyber attacks? [closed]

Is it possible to detect fileless malware attacks with a machine learning model or with any other data science application? Fileless malware exists only in a computer’s random-access memory (RAM), ...
0
votes
0answers
29 views

Interpretation of Loss and validation Loss in Keras

I am building a model to predict one label by taking one feature as an input. The two variables seems to be strongly correlated. I wanted to build a (sequential) Neural Network model with Keras in ...
0
votes
0answers
8 views

Difference between MAP@K for recommendations, MAP from Precision Recall Curves and Macro-Precision

I have been using the 3 metrics independently for a while now, but trying to figure out if they are actually 3 separate things (with similar-looking definitions/names) or there is some underlying ...
0
votes
1answer
15 views

Cross Validation with Artificial Neural Network in Keras

I needed to use cross-validation in the Neural network. I used kf = KFold(n_splits=5, shuffle=True) and ...
0
votes
0answers
16 views

How to improve machine learning model using 2+ datasets

I am building a supervised machine learning model which (for example) predicts heart failure (yes/no). I have two datasets from 2 different labs A and B, which both have decent distribution, aka it's ...
0
votes
0answers
11 views

Classification based on color clustering

I need to classify some domain specific images by analysing their color distribution. I have annotated data; this last classification step is supervised. After some preprocessing and masking and other ...
-2
votes
0answers
20 views

Non linear regression using scikit learn [closed]

What are the different non linear regression techniques and how many of them are available on scikit learn?
0
votes
2answers
21 views

Can identifiers be used to train a model?

I recently participated in some Machine Learning competition where we were asked to decide whether a rider should accept or not a course (~2k riders and ~140k courses). It came up that some of the ...

1
2 3 4 5
180