All Questions

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

Is TransE and DistMult self-supervised?

I am enter to the Knowledge graph embedding and IA in General. I want to know where these two technologies are self-supervised And what is the future of this technologies ?
-1
votes
1answer
14 views

How to approach the dataset with a continuous and discrete label?

Let's say you're predicting the amount of money to bet in a poker game. Based on the game situation, you might decide to fold. In that case, the amount of money to bet is zero. If you decide to call ...
3
votes
1answer
32 views

Can a novelty detection model overfit?

Can a novelty detection model overfit? In novelty detection, the model is trained on normal data instances (not polluted by outliers) where no labels are used in the training process, while validated ...
0
votes
0answers
13 views

Regression Performance varies hugely on shuffling training and testing data

I'm working on a regression problem to predict a variable y based on an input vector X with about 10 columns. To split the data for training and testing, I use the ...
0
votes
0answers
7 views

how to calculate mean average precision of custom object detection algorithms in python

I know that for calculating mean average precision first we must have ground truth files for each image in dataset. I am following this tutorial to detect whether a person has mask on its image or not....
-3
votes
0answers
20 views

Will the total number of $s_t$ variables be dependent on the length of dataset in AdaGrad? [closed]

We update a weight $w$ with Adagrad like this: $$s_t=s_{t-1}+(g_t)^2$$ $$w_t=w_{t-1}-\frac{lr}{\sqrt{s_t+e}}*g_t$$ Where, $lr$ is the learning rate, $e$ is to prevent division by zero, $g_t$ is the ...
-2
votes
1answer
19 views

ML - Labelling - number of possibilities [closed]

I am starting learning ML and stuck with the number of possibilities in labelling. I have a sample which comprises 4 attributes (binary) (from the book Apprentissage artificiel, Antoine Cornéujols) ...
0
votes
0answers
10 views

how to calculate marginal likelihood for bayesian linear regression

I'm learning how to use marginal likelihood/model evidence to choose between Bayesian linear regression models using these notes. The marginal likelihood for the 3 coefficient model greater than the 2 ...
0
votes
1answer
11 views

ANN regression accuracy and loss stuck

I have a data set on predicting solar power generation,the dataset has 20 independent var and 1 dependent. The accuracy of my model is stuck at 60%. I have tried several models but this accuracy is ...
0
votes
0answers
23 views

Machine learning algorithms for identification of Figure of speech

https://en.wikipedia.org/wiki/Figure_of_speech https://en.wikipedia.org/wiki/Rhetorical_device https://www.instagram.com/p/CFn36qVFpBX/?utm_source=ig_web_button_share_sheet Are there Machine learning ...
-2
votes
0answers
13 views

Multivariate time series forecasting using LSTM [closed]

I have a project which is forecasting 4 pollutants based on their past values and 7 weather variables. Now, what I am wondering to know is : can a LSTM model receive all the 11 time series and provide ...
-1
votes
1answer
30 views

What algorithm should I use to get a mapping between two variables? [closed]

I have a dataset that contains for every row, a list X of x items, that is a subset of X_total, and a list Y of y items, that is a subset of Y_total. ...
-1
votes
0answers
11 views

Modeling trend and seasonality in time series retail sales using linear regression [closed]

I am a newbie to the forecasting world. I am working on a project where the goal is to estimate assortment effect on the weekly sales of a product at a retail store. Both location and merchandise have ...
2
votes
1answer
21 views

Why does PAC learning focus on learnability of the hypothesis class and not the target function?

The definition of PAC learning is roughly An algorithm is a PAC learning algorithm if it given enough data, for any target function, it asymptotically does as well as it possibly could given the ...
-2
votes
1answer
39 views

Wouldn't AdaGrad fail in this case? [closed]

This is the update rule for AdaGrad: $$s_t=s_{t−1}+(g_t)^2$$ $$w_t=w_{t−1}−\frac{lr}{\sqrt{s_t+e}}∗g_t$$ Now, let's say we have a data set which has 90 non-sparse features (i.e. features which has ...
-2
votes
0answers
18 views

KNN and Classification Factor [closed]

I'm studying the KNN algorithm and its application on R. If I correctly understood, KNN is a supervised algorithm able to classify an unlabeled item according to the predominant belonging class in the ...
-1
votes
0answers
15 views

How to build Similar Item Recommendation(Non Collaborative) Engine? [closed]

I am working on building a recommender system. I want to build a similar item(non collaborative) recommender system. For example, on an e-commerce website, if I am looking at a mobile with 8GB ram, 16-...
-1
votes
0answers
13 views

CNN wiht input in [0-1] range and ReLU. Won't some channels “die” at initialization? [closed]

I am writing a pretty standard CNN. I'm normalizing my inputs so that the lower value is 0 for each image (and the top value generally isn't higher than 1...). The first layer is a convolution and the ...
0
votes
1answer
24 views

Clustering with TF-IDF and Cosine Similarity [closed]

I'm trying to cluster tf-idf vectors based on their cosine similarity, as such, I was experimenting with taking a given vector, calculating the mean cosine similarity with other vectors in the cluster,...
0
votes
0answers
10 views

Why R output: 'non-integer counts in a binomial glm!'? mixed effects model [closed]

This is my full mixed effects model: ...
-1
votes
0answers
32 views

Is this the reason why we don't just divide the learning rate by the gradient in AdaGrad? [closed]

In AdaGrad, the update equation is this: $$s_t = s_{t-1}*(G_t)^2$$ $$w_t = w_{t-1} *\frac{lr}{\sqrt{s_t+e}}*G_t$$ Where, $G_t$ is the gradient at time $t$ and $lr$ is the learing rate, and $e$ is to ...
0
votes
0answers
12 views

Google Trax's GRU layer

I am learning about Trax for the implementation of GRU and LSTMs. Their documentation says that a GRU layer in Trax can only accept a number of hidden units equal to the number of elements in the ...
-2
votes
1answer
11 views

Numpy failing in subtraction even after same dimensions of arrays [closed]

When I subtract these two arrays, it returns a (354,354) shaped array because as per the documentation there is a mismatch in the shape of the arrays. Why does it happen and what else can I do for ...
1
vote
0answers
21 views

ML method suggestion for regression task

I'm working with a brushed DC motor current, voltage, calculated rotations and measured rotations and a couple of state signals(direction of rotation and the operation state). My objective is to ...
-2
votes
0answers
25 views

Why do we use AdaGrad optimizer with sparse features? [closed]

I have heard people saying that AdaGrad optimizer is best-suited with sparse features. But, why is that?
0
votes
0answers
6 views

How to use time-sequence data with “meta data” of single value per sample? [closed]

I'm, trying to estimate a fish weight by a time-sequence signal of the change in resistance when the fish goes through a gate with electrodes installed. When the fish pass through the gate there's a ...
-2
votes
0answers
22 views

How does the AdaGrad optimizer obtain it's following fuctionality? [closed]

I was learning about AdaGrad optimizer. I came to know that it has a functionality which is that it gives lower learning rates to the features that are more common and higher learning rates to the ...
0
votes
0answers
7 views

Tensorflow: convert PrefetchDataset to BatchDataset

Tensorflow: convert PrefetchDataset to BatchDataset With latest Tensorflow version 2.3.1I am trying to follow basic text classification example at: https://www.tensorflow.org/tutorials/keras/...
-1
votes
1answer
18 views

How do I use lagged independent variable in statsmodel OLS regression?

If there is good reason to believe that an independent variable (x) has a lagged effect on dependent ...
-2
votes
0answers
16 views

Discriminant function [closed]

what's the geometric interpretation of the classifier? For example, what does the angle between $\theta$ and $x$ tell us about the predicted class value? For which angle will y=1? $$ h(x; \theta) = \...
0
votes
0answers
6 views

Python using collection's counter and simple count on dataframe are returning different results for products that are most often sold together

I am following a real data science project on youtube and learning some new scripts and techniques to go around the data and extract insights. The teacher wants to check what are the products that are ...
0
votes
0answers
9 views

Morphological Analyzer for Hindi and English in Python

I am unable to find morphological analyzers for English or Hindi. I am looking for a tool that can split the word into morphemeses e.g. Independently = In + dependent + ly
-2
votes
0answers
9 views

Gradient Descent converge problem [closed]

I have a question about when gradient descent doesn't converge. Problem solved. Thanks for the help
-1
votes
1answer
63 views

Why sparse features should have bigger learning rates associated? And how Adagrad achieves this? [closed]

I was learning about Adagrad optimizer. I came to know that it has a very helpful functionality which is that we can have lower learning rates for the features that are more common and greater ...
-1
votes
1answer
19 views

DataFrame object has no attribute to_frame [closed]

Hi I'm try to figure this code out? and getting this error: the code supposed look like this I got the code from this website.
0
votes
0answers
18 views

How to analyze the abnormal trajectory of the vehicle?

I use this code to mark the latitude and longitude of the vehicle with red points on the map: ...
2
votes
1answer
29 views

One Neural network with multiple outputs or multiple neural networks with a single output?

I an building a feed forward deep learning model using tabular data. The inputs are numeric features or categorical features (represented with embeddings). The outputs are the same number of numeric ...
-3
votes
0answers
19 views

My first Data Analyst job [closed]

I would like to ask you, I’m new to Analytics after finishing my online Data Science Specialization. I got my first work project and I would like to do my best to make it great. My question is, If you ...
1
vote
0answers
15 views

Recommendation Systems User Profile Streaming Data on GCP

I have a recommendation system that recommends articles to different users. I am planning to provide the recommendations in an off-line fashion. Where I already have a table in BigQuery which has the ...
0
votes
0answers
9 views

PySpark: How to reuse a session with getOrCreate()? [closed]

I am building a unit test suite for Spark jobs in PyTest, using this blog post as a starting point. I’ve made quite a few changes to it, but the Session creation is largely unchanged. The proof of ...
0
votes
0answers
13 views

Fastest python graph/network module for finding subgraphs in a multi-partite network [closed]

I'm looking for a python library that is good at finding sub-graphs in a 4-partite network. I call the layers i,j,k & l. In a nutshell, my use case would involve specifying one element in the 1st ...
2
votes
1answer
31 views

how can i visualize the 2d iris dataset

I am doing an exercise on the iris dataset since i am completely new to machine learning. i would like to visualize the dataset in 2d with all six combinations (sepal width-sepal length) , (petal ...
0
votes
0answers
14 views
-2
votes
0answers
7 views

How to deal with huge user-item matrix in recommender systems? [closed]

Recently I was trying to build a recommender system based on collaborative filtering, but my dataset is so big that I can't hold user-item matrix in my memory. I really want to avoid reducing the ...
2
votes
1answer
31 views

How to visualise a large correlation matrix?

I have a dataset with 24 variables, 21 of them numeric. As part of model building I decided to look into the correlation between features and so what I get is a large correlation matrix (21 * 21). Now ...
-3
votes
0answers
17 views

How to perform EDA on dataset with several 100s of columns [closed]

I am trying to start building a regression model using a big dataset. I understand data cleaning and preparation is a critical first step in any model building process. I am aware of all the steps to ...
-1
votes
0answers
16 views

Match between objective function and evaluation metric [closed]

Does the objective function for model fitting and the evaluation metric for validation need to be identical? For example, can an XGBoost model have an MSE objective function (reg:squarederror: ...
-3
votes
0answers
11 views

Is the Glorot Uniform (the default keras kernel_initializer) a random initializer? [closed]

I am wondering if the Glorot Uniform kernel initializer is a random initializer for the Neural Networks weights. The Glorot Uniform is the default initializer used for the Dense layers in Keras.
-1
votes
0answers
16 views

What's the proper input of a ML model for multiple univariate time series classfication?

Summary I'm starting a work on earthquake prediction using machine learning, what I want to do is input some fixed-length time series of accelerometer data recorded today and get prediction of the max ...

15 30 50 per page
1
2 3 4 5
522