All Questions

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

Uniform Convergence and VC Theroy

I've started reading more about statistical learning theory, specifically this paper right here and I cannot understand the following part: It turns out the conditions required to render empirical ...
0
votes
0answers
4 views

Do I have to wrap multiclass SVM in OneVsRestClassifier()?

I am using an SVM for mulitclass classification between 3 labels (1,0,-1). I thought this could simply be done by using SVC(decision_function_shape = 'ovr') in my ...
0
votes
0answers
3 views

Data Loader (imbalanced classes) for Multitask Learning - same input multiple output

I am working on developing an MTL model. There are three tasks in the model, task1, task2, and task3. The classes in these tasks are imalanced and I am stuck at how I should sample from these so that ...
0
votes
0answers
4 views

Is weighted jaccard metric suitable for semantic segmentation?

I'm trying to deal with a binary segmentation peoblem using Unet on Tensorflow 2.0 (Keras module). My classes're higly unbalanced, so I have to use class weights (0.03 for background and 1.0 for ...
0
votes
0answers
6 views

Which activation function of the output layer and which loss function are advised to be used for bounded regression?

I want my (deep) neural network to produce an output from a certain range, in my case between 0 and 255. I have scaled the labels from [0..255] to [0..1]. For the neural network, I have tried a ...
0
votes
0answers
7 views

'float' object is not subscriptable

...
0
votes
0answers
10 views

BERT classifier with Ktrain API is unable to predict new data

I have trained a classifier for sentiment analysis using BERT architecture. I am able to train the classifier and I am getting a validation accuracy of 87%. But whenever I feed in test data, or some ...
0
votes
0answers
12 views

treeExplainer algorithm intuition

I'm reading the paper about the treeExplainer; the pseudo-code of Algorithm 1 is a bit cryptical as most of the variables are not even defined (same with sampling and all details involved). Is there a ...
1
vote
2answers
17 views

Artificially expanding the datasets through rotation of images in MNIST

I came across this question from the 3rd chapter of the book Neural Networks and Deep Learning by Michael Nielsen, this is a question given in his exercise. One way of expanding the MNIST training ...
0
votes
1answer
34 views

find the difference between two columns in specific rows

I have the following columns from one data frame ...
0
votes
0answers
5 views

first predicting subgroups and then combining or the other way around

Assume I have a dataset and want a model to give me a binary output 0 or 1. This dataset is very detailed and has many categories which are subcategories of either the group that yields 0 or the group ...
0
votes
0answers
12 views

Why is the result of each model algorithms (max entropy, forest, svm, etc) producing the exact same output in the tables?

In the R code below, I am feeding in matrix data to help create models based on a series of algorithms (e.g. Max Entropy, SVM, etc). I am having a problem with the algorithm table of results, as each ...
-1
votes
0answers
11 views

Is it necessary to one hot encode while using Pytorch?

I'm doing Image Classification task using Convolution Neural Networks in Pytorch. Do I need to explicitly one hot encode the output labels of Images or Pytorch will handle it ?
1
vote
0answers
10 views

Geometrical Deep Learning Examples

Could you suggest any articles, or work that has been done in the Geometrical Deep Learning field, I was recently exploring Pytorch3D and I was curious about some work that has been done recently.
0
votes
0answers
7 views

Doc to bow vectorizer dimensions are always changing when I re-run notebook

I am running a corpus of tweets through a pipeline, with a SKLEARN wrapper to feed it into a Keras neural network. My problem is that the dimension size of the doc to bow vectors changes from one run ...
0
votes
0answers
8 views

Statistical Test on small sample size (n<30) for non normalized data with MATLAB

Two exams were given and the resulting scores are listed below. Test the hypothesis that there is no difference in performance on each exam versus the alternative that exam 2 performance was poorer. ...
0
votes
1answer
12 views

Multivariate Polynomial Feature generation

I don't quite seem to understand the rules used to create the polynomial features when trying to find a polynomial model with Linear Regression in the multivariate setting. Let's say I have a two ...
0
votes
0answers
13 views

Why does the Neuralnet package predict constant values when a second hidden layer is added?

I'm trying to use a multi-layered neural network to predict concrete strength, using R's neuralnet package. Everything works great with a single layer, but when a second layer is added, the ...
0
votes
0answers
6 views

how to calculate WAR and UAR accuracy when I use SVM.SVC.score in multi-class classifiers?

I used SVM.SVC function to classify. but when I wanted to calculate the weighted and unweighted average accuracy I couldn't access the confusion matrix. because of svm.SVC.score only provides a ...
0
votes
0answers
11 views

Efficient scanning method on images/volumes when applying neural network

I am a newbie in neural network. I am using this for one of my physics problems. So, please forgive my sheer lack of knowledge in this field. My neural network is a convolutional neural network with ...
-1
votes
0answers
9 views

map_table() function

I am trying to use the map_table(t) function from datascience package, the problem is that the geographical map is not shown on the screen although the parameters ...
0
votes
0answers
13 views

Known datasets for long document analysis

Are there good baselines datasets or benchmarks for similarities/retrieval of long texts (extremely long documents, books, etc.)? Although significant both academically and applicational, I cannot get ...
0
votes
0answers
15 views

Any thoughts on analyzing this Time Series

I'm trying to analyze and better understand this time series. More specifically, I'm trying to predict the distribution of the next sample. My initial approach was to plot the histogram, fourier ...
0
votes
0answers
9 views

averaging non-aligned vectors or lists of numbers

I have two lists of vectors: x, and y. Each x,y vector forms a function that can be plotted (see figure). The values in x do not all match, which you can see from the plot. Also, each x vector may ...
0
votes
0answers
8 views

Boolean Classification of Binary Strings using Neural Networks

Suppose that I have a language $L\subseteq \{0,1\}^*$. For each $n\in \mathbb{N}$, let $D_n$ be a dataset containing pairs of the form $(x_i,b_i)$ where $x_i\in \{0,1\}^n$, $b_i\in \{0,1\}$, and $b_i =...
0
votes
0answers
18 views

How to take certain percent of weights from certain featurs in machine learning model?

I am trying to build a ML model that predicts the winner, 2nd, and 3rd place. The dataset has 15 features. However, I would like to have 80% influence of 9 features and the 20% from the rest of the ...
0
votes
0answers
14 views

Free dataset to train a neural network in order to extract text from image

I'm building a custom OCR to recognize and get text from png image. In order to dealing this task, i'm using python with tensorflow library (1.14.0) to develop a Convolutional Neural Network that ...
0
votes
0answers
4 views

Increasing minNumObj increasing accuracy in decision tree

I have been using a J48 classifier in weka and have noticed that increasing minNumObj -- The minimum number of instances per leaf leads to a small accuracy increase. ...
-1
votes
0answers
20 views

How can practically become data scientist [closed]

I am in the IT fields for 15 years and want to get a step change to become data scientist. I am taking the dataquest course online but i am still struggle will people consider me to be data scientist. ...
0
votes
0answers
14 views

Prediction with variable input length

I currently have a model which is trained on all possible input features that seem to be good predictors. The issue however, is that these features are available throughout time, at different stages. ...
0
votes
0answers
7 views

Hidden Markov Model with Autoregressive emission model?

So far, all standard HMM implementations I've seen assume some variation of a Gaussian Mixture (GMM) as their emission model. It can of course only have a single mixture component which reduces it to ...
2
votes
1answer
22 views

GAN Loss Function Notation Clarification

In the Generative Adversarial Network loss function, what do these mean?: $E_{x~p_{data}(x)}$ and $E_{z~p_{z}(z)}$ and how are they used in this context?
1
vote
1answer
52 views

average of 2 classification reports

is there a way to take the average of two classification report? so if I have this two reports ...
0
votes
0answers
6 views

Keras TimeDistributed wrapper Alternative

I have model in Tensorflow 2.0 keras. But I need to deploy this model to 32-bit windows project. I have tried opencv 4.3-dev 32-bit library for inference. But in a model I use ...
1
vote
0answers
15 views

What's wrong with my backpropagation through time (BTT) calculation or how to multiple a scaled vector and a matrix without matching dimensions?

I am trying to make a pretty simple RNN from scracth, using only Numpy library of Python. At this moment I am having troubles with BTT as I do not know how to proceed with situation when a ...
0
votes
1answer
18 views

What is the origin of YOLO/darknet coordinates

I am aware of that darknet/yolov3 outputs relative coordinates, would the coordinate (0,0) be at the bottom left, or at the top left? I am confused as opencv2 seems to have the ...
2
votes
0answers
9 views

Adding high p-value and low R square features in linear regression model to improve result

I am working on a linear regression problem. The features that has been selected for anslysis using both p-value and domian knowledge has improved the model R2 (0.25 to 0.85) and RMSE. Butthe issue is ...
0
votes
0answers
7 views

Issue with custom loss function including parameters in keras autoencoder

I am writing an Autoencoder that tries to find parameters for 3D Meshes. For example how bent an object is. I input the Mesh vertices but would like to include the true parameters versus the ...
0
votes
0answers
24 views

Linear and logistic regression output with same neural network

it seems like this should be a very common task, but I have not found anything useful on my research: How can I do linear and logistic regression with the same neural network? By example, what I mean ...
0
votes
0answers
12 views
0
votes
0answers
9 views

Is Difference Transformation required for LSTM?

I am Working on uni variate multiple step LSTM sequence prediction .My LSTM model is failing to give a good prediction on My Data.From some online blogs I saw that Difference Transform may reduce Data ...
0
votes
0answers
10 views

Tools to do Semantic Anotation on 3d CAD Models

I am trying to do Segmentation on my custom dataset consisting of 3D CAD Models. However, I am not able to find proper tools to generate my dataset for Segementation. I am able to find existing ...
0
votes
2answers
17 views

Which ML algorithm should I use for following use case for classification and Why?

I have data in table format having total 3 columns. One column for label, other two columns are features. So, such 30 rows(1 row contains 2 feature and 1 label) make one set of data with all 30 rows ...
0
votes
1answer
14 views

Question about balancing training data for sentiment analysis (machine learning)

My question is about when to balance training data for sentiment analysis. Upon evaluating my training dataset, which has 3 labels (good, bad, neutral), I noticed there were twice as many neutral ...
0
votes
0answers
8 views

Listwise ranking for query with thousands of docs

Typical listwise ranking model will predict a complete permutation of all docs corresponding to a query q. If the number of docs to one query are large, for example,...
0
votes
0answers
9 views

Creating ANN's (LSTM) for multiple datasets

I have three datasets, each representing time-series water quality data from three different regions (upper, middle, lower regions) of the same geographic area. I want to create different types of ...
0
votes
0answers
6 views

upload model to S3

Hello I'm using AWS Sage Maker to build my model. I want to store the model in S3 for later use. How do you save your model in S3 with Amazon Sage Maker? I know this seem trivial but I didn't ...
0
votes
1answer
14 views

What is the best way to match street addresses in a dataset in Python?

I have a dataset of land parcels owned by the government and I am attempting to match street addresses to an existing list of government agencies. I've used fuzzy matching and used a regex that ...
0
votes
0answers
14 views

How do I discern document structure from differently-tagged XML documents?

I have a body of PDF documents of differing vintage. Our group had exported the documents as text to feed them into a natural-language parser (I think) to pull out subject-verb-predicate triples. ...
1
vote
0answers
14 views

Do I need to adjust frequencies or weights of rows so the right weight is given to each sample (data mining)?

The general problem type is as follows. I have about 2,500 rows of data. Each row contains data about an individual sample with sizes from around 10,000 to 200,000 (a known attribute / column), and ...

15 30 50 per page
1
2 3 4 5
464