All Questions

I have a small problem with a feature and I don'T know how to go around it to make it usable, so I would be really happy if someone can give a tip to solve this. The problem: I have a feature that ...

While experimenting with transformers' TFBertForSequenceClassification and BertTokenizer, I noticed that BertTokenizer: ...

I'm trainig a SSD MobileNet V2 FPNLite 640x640 object detection model on custom dataset, I undorstood that to make the model train faster is to change the parameters of anchor_generator for example, ...

BLOCKING_ENABLED=true PIHOLE_INTERFACE=eth0 IPV4_ADDRESS=10.8.0.1/24 IPV6_ADDRESS= QUERY_LOGGING=true INSTALL_WEB_SERVER=true INSTALL_WEB_INTERFACE=true LIGHTTPD_ENABLED=true DNSMASQ_LISTENING=local ...

I'm trying to solve a time series forecasting problem, where the main goal is to read data with various alarm logs and make a prediction about what may happen in the future. Specifically, my data is a ...

I have a multi-class classification neural network. After applying softmax to the last layer, I pick the class with the max value. My question is Like it is possible to tune the recall and precision ...

I'm trying to use machine learning for security event classification. My goal is to predict the outcome (true positive or false positive) of a specific event. An event has a set of variables in it, ...

I want to drive from Seattle to San Francisco, and I've some time for sightseeing: what route should I choose to eat nice food and on my way, see some beautiful sides? I would model the world as a ...

In the case of object classification, what parameters do we learn from training examples? Do we learn mean and standard deviation? Let's say if I had 50 images with ground truth bounding boxes and ...

I am planning to use BeautifulSoup to extract articles where the keyword "Microsoft" or "IBM" is mentioned. Preferred websites are: Google News Bloomberg New York Times Yahoo News ...

I am looking to know if there is a data system that handles the following use case. To keep it simple, the data is a set of homogeneous enties E. E contains named numeric properties that the app code ...

I am curious how it is done as I am interested in doing something similar. I have some manually transcribed data that contains tags for multiple speakers. I want to compare how well the out of the box ...

The Louvain method for community detection aims to optimize modularity and hence detect communities in the given graph. In case of a weighted graph would it be valid to assume that an edge with a ...

I want to use MonteCarlo function in MonteCarlo package in R which has one requirement among ...

I have a folder that lives within a sharepoint drive url. I wish to automatically extract a certain file, df, within this folder and import this file using Python. Desired Result: To schedule a 'job' ...

Machine Learning books generally explains that the error calculated for a given sample $i$ is: $e_i = y_i - \hat{y_i}$ Where $\hat{y}$ is the target output and $y$ is the actual output given by the ...

Suppose we have k groups of points located closely to k lines. These k lines are parallel to each other. How can we estimate the slope of these parallel fit lines? Here talks about the case when k = 1,...

I'm creating a neural network in tensorflow and need to minimize the following loss function: $\frac{max(y,p)}{min(y,p)}$ Where $y$ represents the true value and $p$ the predicted value. Since the ...

How can data science teams measure and improve costs of their technical work, when they often don't know the monetary value of the datasets and insights they are producing? Are they using industry ...

I am new to DNN still learning, have a need to build item-to-item content based recommendation using DNN. For example, say I have a column of strings where each row represents a document I need to ...

I have a table that has information about specific events. Say I have a list of people, Andrew, John, Mary, who may do different actions during the day at specific times. My table then looks like: <...

I read many time that for machine learning and data mining algorithms the multi-dimensional input data should be scaled (e.g. normalized or standardized). Now my question is whether the average, min ...

I've conducted a couple studies examining how "risky" several web applications are based on whether the respective support teams raise a major incident ticket. The data we have includes the ...

I am working on face matching model (matching between id-card faces and selfies), where I am using the resnet50 pre-trained model from ...

I was wondering about hyperparameters used in Deep Q-Networks. Considering the use of replay memory and target network, together with the epsilon-greedy policy, are the number of epochs different of 1 ...

LSTM's carry a hidden state and a cell state with them. Now, in a standard encoder-decoder model, we pass the Context Vector from the encoder to the decoder. Does, this Context Vector consist of just ...

Basically the title asks my question. I have the results of a survey that was filled out by people from different countries. I have been asked to analyze the data using PCA and see what findings I can ...

I have to do an Econometrics project about the sales of electric cars in China in the last 10 years by finding a possible relation between the level of pollution and the oil price.

I have trained a BERT model using ktrain (tensorflow wrapper) to recognize emotion on text, it works but it suffers from really slow inference. That makes my model not suitable for a production ...

I’ve difficulty in understanding LSTM input shape. For example. I’ve 2 videos out of these 1 is categorized as Awake (0) and 1 as Drowsy (1). I preprocessed them to extract Eye Aspect Ratio and Mouth ...

Edit Thanks to the answer of @pcko1, I understand that I should use data augmentation to make my model resilient to order of data points. Clarification after the answer of @Icrmorin : My problem is ...

I have number of aerial/satellite images of a forest taken over 10 years. I wanted to create a heatmap of changes over time of the area. I was able to find tools to create diff between 2 images, but ...

Recently I've been working on a pretty vanilla ANN model in Python with sklearn (and its preprocessing pipeline), mostly in jupyterhub notebooks if that matters. I am considering changing the ...

This is the problem of binary classification: "1" - the subscriber is a driver (belongs to the segment of drivers), "0" - the subscriber is not a driver (does not belong to the ...

In reinforcement learning, normal distribution is commonly used for continuous actions. I'm checking Pytorch's implementation for KL divergence between two normal distributions. I know it's impossible ...

My lecture slide told me that if we don't prune the regression tree, then the tree likely to over-fit. So, I wonder why would that happen? Is that because if the tree grows too large, we would end up ...

I want to use LighgbmClassifier for a binary Classification. for Hyper Parameter tuning I want to use Hyperopt. The Dataset is imbalanced. Using Sklearns class_weight.compute_class_weight as shown ...

I have a scenario that I have one-dimensional data and the distribution of the data is not Gaussian. (more like a bimodal distribution). I want to find an anomaly detection model that could predict ...

I am taking a course that introduced me to sklearn.ensemble.RandomForestClassifier. At first it uses n_estimators with the default value of 10 and the resulting ...

I have started a project to find out good combination of courses. I have a dataset containing studentid, courses taken, grade for the course and final gpa. I am thinking, to get the students who have ...

I am training a model to detect buildings from satellite images in rural Africa. For labels, I use OpenStreetMap geometries. I use the Tensorflow Object Detection API and SSD Inception V2 as a model. ...

I have precipitation satellite data of different resolutions: one is a 4.5 square kilometers and the other is 10 square kilometers. What would be a sufficient way to combine the two for further ...

Sometimes you might want to check your ideas on multiple datasets. There are several places with datasets collections. Question: Please share some Python scripts how to download multiple datasets from ...

I've found this equation that explains the output of a neuron in a MLP network: $y(n) = f(\mathbf{w}^T \mathbf{x}(n) + b)$ I can understand the general context, but since i have no background with ...

I plotted a learning curve below. There is a thick red band around the top portion of my training score. Why is it so high at the beginning? Below is a snippet of the code used: ...

Does the output generated from the LSTM encoder module exist in the same semantic space as the original word vectors? If so, say for example we have a sentence and we pass it through the encoder to ...

I would like to print the f1-score. I got confused about the wording f1-accuracy score and accuracy score. What is the difference of these 2 scikit-learn metrics and how can I print the f1-score out ...

I am applying OCR on pdf documents and later processing the content of them. I am having problems when trying to split into paragraphs: normally, one "\n" means an end of line while "\n\...

I really do not understand what does this code do M = sparse.coo_matrix(([1]*n, (Y, range(n))), shape=(k,n)).toarray() The code is related to calculating the ...

from sklearn.metrics import confusion_matrix for i in range(len(model)): print('Model',i) cm=confusion_matrix(Y_test,model[i].predict(X_test)) TP=cm[0][0] TN=cm[1][1] FN=cm[1][0] FP=cm[0][...