All Questions

8,076 questions with no answers
Filter by
Sorted by
Tagged with
0 votes
0 answers
114 views

Why is the batch size same as before?

In the following code, I first declare a, b as tensorflow placeholders for initialising iterator ...
ab123's user avatar
  • 205
0 votes
0 answers
138 views

advice on distance metric for knn w/image recognition

I'm getting my feet wet with machine learning and am implementing a knn algorithm on a dataset that i've created. I've created a set of images of circles and squares and want the knn algorithm to ...
sf8193's user avatar
  • 109
0 votes
0 answers
583 views

FastAI to PyTorch conversion

I have been taking the FastAI course. And if anyone else has taken this course they know that they use their own python library called fastai that is a wrapper for ...
conv3d's user avatar
  • 221
0 votes
0 answers
170 views

How to avoid one hot encoding again and again on each run

I have a dataset which is categorical. I did one hot encoding in the train data which is taking much time for each run of my algorithm. I have also performed one hot encoding on the test data which I ...
Bishakha Kumari's user avatar
0 votes
0 answers
107 views

Encoder-Decoder performance time

I have two encoder-decoder models. *First model: *Second model: When I check the performance of the models I get approximately the same performance time (First model ~ 42 sec, Second model ~ 40 ...
Sabrina's user avatar
  • 23
0 votes
0 answers
227 views

Low MSE loss for object detection but really bad results

I am training object detection using CNN I am using MSE as loss functions, at best it throws loss around 1800 on testing and 1850 on training data, Which in my opinion is quite acceptable, considering ...
trolkura's user avatar
  • 135
0 votes
0 answers
885 views

plot the results from kmeans

I am trying to plot results from document (data source: twitter) clustering using python's sklearn. Below is 10-words of words belonging to each cluster: ...
lpt's user avatar
  • 129
0 votes
0 answers
61 views

My weight matrix converged to zeros

So I was training a fairly shallow convnet, because my deepnet based on vgg19 wasn't working. 2 conv layers and 2 flat layers, the second flat layer was the output. It converged quickly to all zeros ...
Ryan's user avatar
  • 722
0 votes
0 answers
101 views

Incorporating new features in document similarity task

I have a model pipeline for finding similar text documents given an input query text. The model is very simple; I have a corpus of documents on which I train a TfIDF model. When a query is input, we ...
PyRsquared's user avatar
  • 1,614
0 votes
0 answers
542 views

Keras - Why Validation data produce good results, while unseen data is performing poorly

I've built a feedforward net that predicts 2 classes (0,1). I've used the validation_split attribute like so: ...
Shlomi Schwartz's user avatar
0 votes
0 answers
445 views

Ideas for using polynomial regression for multivariate time series prediction

I would like to predict next 12 months of employee count based on 3 or more years of data that includes salaries, profit and employee count. I have also interpolated monthly values for these three ...
Moki's user avatar
  • 9
0 votes
0 answers
106 views

Categorize text as Body, Heading in a loosely formatted document

Given a semi-structured document with only texts and images, and some style properties present on the text, What is the best possible way to classify the text present in the document to any formal ...
Abhay Sibal's user avatar
0 votes
0 answers
1k views

How to improve the accuracy of Random Forest for Text Categorization

I am working on a text Categorization problem, the objective is to classify related companies into their corresponding categories. This is a single category classification problem and not multi-class ...
Ahsan Nawaz's user avatar
0 votes
0 answers
259 views

How to use a Neural Network to classify a very large number/bit string?

How would I set up a NN to classify a cryptographic key for asymmetric cryptography, or generally a VERY large number/bit string? I could split this bit string into bytes/16bit/32bit/64bit numbers to ...
Radovan Bezak's user avatar
0 votes
0 answers
84 views

RNADE vs MDR vs BART vs Bayesian Linear Regression

I'm looking at a collection of problems where I need to forecast the probability of a continuous variable. My dependent variables are a combination of categorical and continuous. It looks like there ...
David's user avatar
  • 9
0 votes
0 answers
1k views

Deep Reinforcent Learning Model, experience replay

So I am working on a deep RL model in OpenAI Gym. I have everything else working except for my function that allows my agent experience replay. here is the code: ...
hisairnessag3's user avatar
0 votes
0 answers
83 views

Maximum Dimensionality of AWS Machine Learning

I am toying with AWS Machine Learning and I have a dataset with about 200 records with about 220,000 variables each. Apparently, AWS Machine Learning has a hard limit of 1000 variables. How can I ...
719016's user avatar
  • 109
0 votes
0 answers
1k views

Feature Importance and Partial Dependence plots seem to disagree?

I need some help understanding my partial dependence plots for binary features passed to a GradientBoostClassifier when comparing them to the feature importances. For some background, my goal here is ...
Dan Carter's user avatar
  • 1,742
0 votes
0 answers
209 views

Algorithm to create graphics from scribble

I want to implement a system that takes as input scribbles (i.e. drawings with writings on paper, input to the algorithm is a photo of this) and outputs the forms / writings e.g. in Powerpoint. What ...
Chris's user avatar
  • 9
0 votes
0 answers
539 views

HMM - Matlab for data set to detect anomaly

I have a dataset of oil temperatures. The time series consist of 100 hours of measurement at every second. There is an anomaly in the data that I would like to detect using Hidden Markov Models (HMM). ...
Suresh's user avatar
  • 9
0 votes
0 answers
87 views

binary longitudinal time series

What kind of feature engineering techniques should one apply for longitudinal data comprising of individual binary time interval data about when an activity was done during the day(we have this data ...
ron's user avatar
  • 9
0 votes
0 answers
1k views

Entropy calculation for MNIST dataset to form classification decision tree

I am trying to get classification tree in R. I am using MNIST (handwritten digit dataset) to train my decision tree. The dataset has 28*28 pixel box. Pixels are organized in row-wise. Pixel values are ...
user12395's user avatar
0 votes
0 answers
265 views

Analyze paragraphs using Neuroph

Currently we are regularly analyzing sets of paragraphs every month. I would like to automate this and split each paragraphs into chunks of data. To do this I would like to employ a neural network. ...
Robby F's user avatar
  • 109
-1 votes
0 answers
12 views

Difficulty learning binary classification for 'very similar' inputs

I have been struggling to train a classifier to tell the difference between 'bad' and 'good' datapoints for a physics application. Essentially I am inputting as features some parameters that are used ...
Wigeon's user avatar
  • 9
-1 votes
0 answers
8 views

Custom Named Entity Recognition (NER) Model with spaCy V3

This is my first time building a custom model with SPACY NER. ''' Define a function to create spaCy DocBin objects from the annotated data def get_spacy_doc(file, data): Create a blank spaCy pipeline ...
user163197's user avatar
-1 votes
0 answers
14 views

RuntimeError in a Simple QA model using Transformer

I am new to transformer architecture. I am trying to build a model that will generate answers to questions. For simplicity, I am using three sample questions and answers in a pandas dataframe. After ...
Ishrat Hossain's user avatar

15 30 50 per page
1
158 159 160 161
162