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
0 answers
3 views

How to solve Nonlinear least squares problem?

Initial idea is to use euclidean distances. But I do not understand how should I solve this task.
user avatar
0 votes
0 answers
6 views

Trimming "unused" neurons from the bottleneck of an autoencoder

I'm working with autoencoding data in segments, and working with the latent space afterwards (I am also working on VAEs, but this segment of the project concerns deterministic AEs). I've noticed that ...
user avatar
  • 101
0 votes
0 answers
10 views

Will removing one support vector affect others?

Supppose we have SVM trained on a dataset and the support vectors are $SV=\{x_1,x_2,\cdots,x_n\}$. Then, we know that the decision plan is decided by $SV$. My question is that if we remove one support ...
user avatar
  • 101
0 votes
2 answers
25 views

How much percentage of outliers are allowed in a data

I am buliding a machine learning model with logistic regression. I am dealing with blood transfusion data set. In which there is a feature,Total_volume, I found that there is more than 5% of outliers ...
user avatar
0 votes
0 answers
12 views

Reducing the dimensionality of entire dataset

I have a lot of datasets with different shapes. For example few of them are (90, 892), (74, 853), (93, 765), ... etc. I want to convert this shape to (90, 4), (74, 4), (93, 4) ... (x, 4). And, after ...
user avatar
1 vote
1 answer
16 views

Difference Between Attention and Fully Connected Layers in Deep Learning

There have been several papers in the last few years on the so-called "Attention" mechanism in deep learning (e.g. 1 2). The concept seems to be that we want the neural network to focus on ...
user avatar
  • 536
0 votes
0 answers
10 views

How to use the SHAP library in an existing CNN model

I'm a new student at DL. I want to use the SHAP library (KernelExplainer) to explain an available code using a Conv model which is defined in this path: network.py and then calls the Conv model in ...
user avatar
  • 1
0 votes
0 answers
9 views

How to train SentencePiece tokenizer for huggingface transformers?

I am trying to train MarianMT model using Huggingface Trainer API. But first, I need to train MarianTokenizer which needs three parameters to initialize: Processor for source language Processor for ...
user avatar
0 votes
1 answer
23 views

Denoising in ML Pipeline

Say I split my raw data into train and test sets. Should I clean them first and denoise the datasets before I start creating new features or, should I create new features for both the train and test ...
user avatar
0 votes
0 answers
8 views

why are there different formulas for sample and population variance?

I don't understand why there are different formulas for sample and population, and also sometimes when we calculate the variance, we get sample variance > population variance. Why's that ?
user avatar
0 votes
0 answers
16 views

Training with code scripts to achieve a specified goal?

I am quite new to machine learning and therefore need to ask if some ideas might be possible. Imagine an application that is managing the state of an Actor by ...
user avatar
  • 101
0 votes
0 answers
29 views

Are there tools that would run many machine learning fits without much setup?

Are there tools that would run many machine learning fits without much setup? Such tool could be useful for discovering what kind of model could be the best fit, without trying each of them manually.
user avatar
  • 387
0 votes
0 answers
14 views

How "much" should belief be weighted against numerical measures of accuracy/correctness?

How "much" should belief be weighted against numerical measures of accuracy/correctness? It's possible to devise numerically low-quality models, but that have very good empirical validity, ...
user avatar
  • 387
0 votes
0 answers
13 views

IKM Data Science Assessment

Has anyone ever given an IKM assessment for a technical interview? - it's a general assessment that companies use to measure your skills.
user avatar
  • 1
0 votes
0 answers
15 views

Validation Loss and Training Loss Gap

I am trying to train an LSTM model. Here is the train and validation loss graph: What does this mean? Is the model not learning? Thanks! I'm new to ML so would appreciate anything!
user avatar
0 votes
0 answers
8 views

Cross validation on train set or entire dataset

I have used train test split to split the entire dataset into train 80% and test 20%. Then i have used the cross val score with 5 folds on the X_train and y_train and got the max accuracy of 99.76 and ...
user avatar
0 votes
0 answers
16 views

How Can I find the medical image datasets for congenital heart defect

I am working on implementing the image segmentation model for diagnosing a patient with a congenital heart defect. But I couldn't find the image datasets. please, anyone, help me to Find the Image ...
user avatar
0 votes
0 answers
11 views

Mask R-CNN (matterport) does not generate masks or just generates them randomly

I'm working on a project detecting two different types of olive branches. I'm following this code (based on matterports Mask R-CNN) with my own dataset: https://github.com/AarohiSingla/Mask-RCNN-on-...
user avatar
0 votes
0 answers
8 views

Is 500 epochs too much for a CNN project?

I am working on a project where I need to train a model with a data set of 250 images. My epochs count is 500. Is that too much? Will it overfit? I did this because ...
user avatar
0 votes
0 answers
4 views

Algorithms for single output based om multiple inputs

I have a data set in which for every single x value, I have two y outputs. Example: X1=2 gives Y1=3,4; X2=9 gives Y2=122,89; X3=19 gives Y3=245,109; Now, given two y values for each x value, I want to ...
user avatar
0 votes
0 answers
10 views

Classifying Hot Drinks

I have a university project in which I will attempt to build a machine learning algorithm to classify images of hot drinks (e.g tea, coffee, etc) and I was wondering about the best approach to do this....
user avatar
  • 1
0 votes
0 answers
18 views

Difficulty of training deep neural networks

While training neural networks I'm trying to debug what is wrong however not sure what to look at. From paper "Understanding the difficulty of training deep feedforward neural networks" by ...
user avatar
  • 355
0 votes
2 answers
23 views

If sigmoid activation function is prone to vanishing and exploding gradients can we not use it in final layer of binary classfication?

Many paper and books say that sigmoid activation function with random intialization is prone to vanishing/exploding gradients therefore it is better to use LeakyRelu, Elu, or Relu. Does this mean that ...
user avatar
  • 355
0 votes
0 answers
7 views

How to add an Attention Layer to a BiLSTM Model on Keras, with additional data query inputs?

I am trying to replicate a BiLSTM model that I read on this article. The Attention Mechanism that they use is proposed by this other article. I have a BiLSTM Model without an Attention layer that is ...
user avatar
0 votes
0 answers
29 views

How to train models when the goal is to maximize an objective function on only the unknown part of the features space with a high score?

We have input features and features space - X and output target - Y (continous or discrete). The connection between X and Y inside small part of features space (A) is stronger than inside rest of ...
user avatar
0 votes
0 answers
6 views

How to use GBDT with EFB or GOSS with EFB in LightGBM? or is it implemented by default?

The paper for Lightgbm talks about goss and efb, I want to know how to use these together. I know of the hyper-parameter 'boosting' can be used to set boosting as gbdt, or goss, or dart. But how to ...
user avatar
  • 27
0 votes
0 answers
13 views

metric that describes the chaotic nature of a timeseries

I'm doing timeseries modelling and I want to parameterize the randomeness seen in the first picture compared to the second one. I have the standard deviation as input to my model but I'm looking for ...
user avatar
1 vote
1 answer
38 views

Why Multicollinearity is a problem in machine learning algorithms

Is only a subset of algorithms are affected by the multicollinearity problem or all the machine learning algorithms? What is the solution for this?
user avatar
0 votes
0 answers
7 views

Does Field of View in Camera affects the performance of Keypoint detection and semantic segmentation model?

I have two cameras to capture images for training keypoint detection and semantic segmentation model. One camera has smaller field of view and the other has larger field of view. Let's say, I capture ...
user avatar
0 votes
0 answers
11 views

What is this method of feature selection called, is it a good idea, and if so how might I implement it?

I hope you don't mind me asking a few questions in one - they're all related somewhat. I'm working on a simple classification problem (Titanic, you guessed it) and I'm trying to grind out the last ...
user avatar
0 votes
0 answers
19 views

Evaluate predicted values compared with labels and actual value

I have generated a range of predicted data. I also have the label and an actual representation of the data. How do I evaluate if my predicted data is any good? The predicted value represents the ...
user avatar
  • 1
1 vote
1 answer
11 views

Pulling out Training Data from another Dataframe

I'm trying to do a Random Forest Regression on a geographical dataset. I'm hoping I'm doing things right, and if anyone can see an issue with this please let me know! Problem: I have an area, with a ...
user avatar
1 vote
0 answers
8 views

How to implement simple VAE with sparse tensor in Tensorflow

thanks for reading. I have been attempting to train a simple VAE on very sparse 2D and 3D data. So far I have been training using dense tensors which - I think - is resulting in horrible training due ...
user avatar
  • 11
0 votes
0 answers
8 views

Categorical features in Factorization Machines

How should categorical features be encoded to substitute values for x_i and x_j when modeling Factorization Machines? The large number of categorical variables makes one-hot encoding impractical. ...
user avatar
0 votes
0 answers
15 views

Machine/Deep learning model for object labeling in Check Images?

I am currently facing an issue with identifying sections within a check images, something like object identification. Initially it seemed I could use YOLOv5, because it is good with object detection. ...
user avatar
0 votes
0 answers
14 views

What are the types of Fine-tuning and the mathematical equations of fine-tuning in NLP [closed]

What are the types of fine-tuning in NLP, where can i get the mathematical equations and detail explanations of fine-tuning process. thank you very much in advance.
user avatar
  • 1
0 votes
1 answer
20 views

How to build correct dataset for ann classifier?

I have x signals each with 5000 rows. Each signal x has its own one output in range from 1 to 6 (categories). So for example signal x1 has output 2, signal x2 has output 1. How can I build X and Y ...
user avatar
1 vote
2 answers
59 views

Probability each day till payment

I'm tasked to predict if a receipt will be paid or not. I know how to build a classification model that says, on day 0, if the receipt will be paid or not. But how would one build a model to run ...
user avatar
  • 11
0 votes
0 answers
21 views

Procedure or term for analyzing transcribed text and returning bulleted output

I am attempting to analyze transcribed text from an audio file to group bullet points based on known key phrases in the text. Example: I have verbally stated the following keywords in the text, which ...
user avatar
0 votes
0 answers
10 views

How to debug a neural network

After training wide& deep model for recommendation, weights of final layer becomes 0 leading to score of 0 for all inputs. I would like to know why this is happening and try weight initialization, ...
user avatar
  • 355
1 vote
1 answer
28 views

How to build a predictive model with multiple features?

I built an R RandomForest Regression model. The source training data is a historical monthly report of all closed tickets, and the data for forecasting/prediction is a report of open tickets. These ...
user avatar
  • 113
0 votes
2 answers
31 views

If you are making a ensemble model does training data on base models have to be different from one another

I was reading this article talking about ensemble models. I was interested in the max voting model using 3 base learners. However, I am a little confused about the process. Currently, I'm thinking it ...
user avatar
  • 13
0 votes
0 answers
8 views

LSTM Input for features/timesteps and locations/features/timesteps

I have seen time steps, units, batches, samples, sequences, features and more terms seemingly as if they are self-explanatory and yet all describing only in total 3 input dimensions to LSTMs. If I ...
user avatar
  • 71
1 vote
2 answers
78 views

Predict parallel time intervals

I have the following problem. There is a service station that can provide service for a number of vehicles at the same time. The service data looks like this: ...
user avatar
0 votes
1 answer
18 views

Do I need training data in multiple languages for a multilingual transformer?

I am attempting to train a transformer which can categorize sentences into one of n categories. This model should be able to work with a number of different languages - English and Arabic in my case. ...
user avatar
  • 189
0 votes
0 answers
11 views

How to do a batch trainning of Pytorch model without using Dataloader?

I am doing a time series data training. I have to pad 0s to the data so the sequences have the same length. Because of 0s are padded, I have to mask them during the training, for Keras, it is simply ...
user avatar
  • 1
0 votes
0 answers
10 views

Creating tables from unstructured texts about stock market

I am trying to extract information such as profits, revenues and others along with their corresponding dates and quarters from an unstructured text about stock market and convert it into a report in ...
user avatar
  • 11
0 votes
4 answers
35 views

Where to learn which ML task is most appropriate for a problem?

There is now tons of material available on how to do certain (most popular) ML tasks and what kind of output you can expect. However I found that resources on how to select appropriate ML task/...
user avatar
1 vote
1 answer
14 views

Certain Image Augmentation Prevent Unet Model from Learning

I am training a Unet model for cell image segmentation from microscopy images. In order to help the model generalize better to different microscopes, I attempted to apply brightness augmentation to ...
user avatar
2 votes
2 answers
475 views

Suggestions for guided NLP online courses - Beginner 101

I would like to know from the data science community here for suggestions on nlp courses. I am new to NLP area and would like to take up a course which covers from basic to advanced concepts such as ...
user avatar
  • 2,275

1
2 3 4 5
212