All Questions

There are various ways to increase the resolution of tensor in (width, height) dimensions, frequently used in detection models like ...

I have seen some people change the datatype(from object to category) of the feature they want to encode.

I have a population of $n$ items to label and a budget to label only $m$ ($m << n$) of them before training. The population can be partitioned into subpopulations, recursively. In other words, ...

I've read in a few published papers that it is possible to improve a model's accuracy by adding location and contextual information to the images. I'm interested in applying this to my CNN model. Does ...

I am trying to implement the SeGAN paper with this repository: GitHub repository for SeGAN I installed the prerequisite and tried to train the model with: ...

I have an excel sheet of the form ...

I want to extract features from pre trained ResNet model for over 2M data. Problem? Even with the average pooling applied on the last layer's result, it provides a ...

I am using Pytorch-Geometric library to implement a Graph Convolutional Layer(GCN) followed by few linear layers for a prediction task. But after training on graphs with np. of nodes being 10K and no. ...

I am currently studying Machine Learning course and now we are requested ( each student ) to find an Image dataset to work on for the course project. I am new to ML and it's now a week and I am trying ...

What is the typical accepted range of gamma and min_child_weight parameters for the XGBoost algorithm? Is the range of min_child_weight correlated with the number of feature or samples in the training ...

I have a very basic question, when I'm adjusting weights and biases in a NN, should I: Forward propagate and backpropagate to calculate gradient descent (DC) for each batch once and then repeat for <...

What methods might one use in order to find and analyze cause-and-effect in a dataset? An example might be something like plotting this: ...

I've been trying to follow this paper on Bayesian Risk Pruning. I'm not very familiar with this type of pruning, but I'm wondering a few things: (1) The paper describes risk-rates to be defined per ...

I'm using a reviews data and trying to apply classifier model and get prediction. Here is the code i'm trying. ...

I am working on a project that involves picking out specific kinds of objects from text. The documents I am going though are life sciences and biomedical in nature, and in these documents there are ...

I just started to learn on ANN and tried to experiment on my own on a Linear Regression. I got a dataset which had housing prices for a city. Tried going through this but my model gives me a huge loss....

I need some advice for my feature engineering. Suppose I have 90 days follow-up data. on 12 patients and I have the vital status of the patients at the end of these 90 days (deceased=1, alive=0) ...

Can you suggest some google analytics metrics such as (click or impressions etc) to evaluate a recommender model deployed on an e-commerce website.

I think the title is enough for what is my problem here. I have 100 tickers in a folder. I got all csv files to one list. but I wanna see the tickers name which these are csv file names. what should ...

How do you use SOM as a supervised learning technique? Which approach can be added to SOM to turn it to supervised learning?

I am stuck on a problem where I want to save a custom model that is trained using a custom training loop that needs to both be able to take in arbitrary input shapes during inference, and also be able ...

I am working on a document classifier that can perform the classification based on the document structure as well. My plan is to get the word embedding as well as the word coordinates and somehow ...

Some time ago I was reading a book on machine learning in which they had an example that would take some data and try to determine based on weather, temperature, humidity and Wind if a sports team ...

There is a set of 3 variables in 200 rows. The mid number among 200 numbers which means ID = 100, is important and I would like to know how much it affects each of the points before that number(ID=100)...

I was trying to implement SRGAN in PyTorch and I have to write a Content loss function that required me to fetch activations from intermediate layers for both the Generated Image & Original Image. ...

The terms Time Series Analysis, Time Series Forecasting, and Time Series Modeling are widely ...

Generators based on the transformer architecture predict the next token based on given previous token. So you can give "Today is" as input to a transformer and it will create a sentence or ...

I'm looking for an open source tool to assist my colleagues and I to label images for a machine learning application. We don't actually need bounding boxes or anything to pinpoint regions within each ...

in Roberta if NSP loss is not used , what is the loss function for DOC-SENTENCES or FULL-SENTENCES task , on what basis will it update the weights ?

College restricted us to make projects in object oriented programming languages but without using any other libraries except standard ones. We can not use APIs also

For 20M + images, I'm thinking about using LSH for similarity of Vectors or data points or more precisely image Embeddings ...

I have a list of sentences returned as a result of a document search algorithm. I want to determine if the results returned are semantically close/similar/coherent using some sort of metric. For a ...

I have the following: Training set - X values mapped to 4 different y values [400x5] Test set - X values mapped to 1 y value [400x2] The objective is to get the best function which minimizes the LSE....

I am studying latent factor model for recommendor system. It does matrix factorization(like SVD) on the user-item rating matrix. What I am not sure is, does a trained model work for a new user that is ...

Let say we have bunch of feature and we only have two group or label (say A and B). What i want to do is to define best value as a cutoff to separate both Group A or B. If value of each feature are ...

i've been studying gradient boosting so realize the pure algorithm requires a function F/model to get boosted.What is the explicit F on gradient boosting trees?

I have a logistic regression classifier that shows differing levels of performance for precision and recall at different probability boundaries as follows: The default threshold for the classifier to ...

The text and output to be extracted are similar to the following : "Check it every two weeks" - two weeks "Check it on day 1 and day 14" - day 1 and day 14 "day 19 and day ...

Design an application which will have all operations like create, update, delete, display employees using MongoDB database. Front-end should be in HTML and CSS backend should be in PHP Design ...

I created a customer retention grid that tracks customer counts by territory by year. The sales managers have loved it. The numbers were terrible, but now they know what they didn't know and can ...

I was implementing the SRGAN in PyTorch but while implementing the discriminator I was confused about how to add a fully connected layer of 1024 units after the final convolutional layer My input ...

I'm writing a code to make movie genre classification with movie posters. I opened a github repository where I put all the posters and cloned it on Colab. Until here, eveything works fine. When I'm ...

Is there any way to convert the detected object from an object detection algorithm (Mask RCNN in my case) to a white silhouette (while the background has been set to black)? I have commented on the ...

If I have the following example: How should I annotate the bottom image? I can think of those scenarios: Create a large box that captures class B and a second box that captures entirely class A. ...

When I visualize data using matplotlib it displays very well, but when using Plotly, the data display very bad.

Once the text is converted into a vector of size(1,100), how can we interpret and backtrace a word's importance which helped in classification?

I did a study in which around 1000 participants took a test (100 questions). In this study participants were asked in each question to choose between two texts (text 1 and text 2) and decide which ...

I want to get inference of 2 models. First model(Runs at 20fps, Pytorch), Second one is a heavier model(Inference time 1 sec, Tensorflow) on webcam feed. The first model would be running on every ...

I'm using the tsfresh library to extract features on my data but I keep getting an error: ...

Why having a symmetry of values for the hidden state imply that the neural network is non convex? I could not find an intuitive answer for this yet. Also, if we consider a Fully Connected network wtih ...