All Questions

6,141 questions with no answers
Filter by
Sorted by
Tagged with
0
votes
0answers
27 views

How to handle missing data in a logistic regression?

I am building a model to solve a binary classification task. So far, the input is low dimensional (10 dimensions at most). I need to face the occurrences of missing input. It is my first time at ...
0
votes
0answers
42 views

Wikipedia corpus for NLP - Cleaned sentences

I can see many wikipedia dumps out there. I am looking for a wikipedia-made corpus, in which every line is one sentence, without any wikipedia meta tags.
0
votes
0answers
22 views

Neural Network for classifying input data to maximize accuracy

Recently I've been working on some deep neural networks for binary classification, and in developing the appropriate features, I found the necessity to classify the input data. For example, if the ...
0
votes
0answers
892 views

What is the best way to implement skip connections in a Dense Network in Keras?

I want to use skip connection in a Dense model and I chose the following implementation of the idea: That is I use a Dense layer with linear activation to map the input into a dimension that will ...
0
votes
0answers
72 views

Latent Dirichlet Allocation in R, topicmodels using VEM algorithm or Gibbs Sampling mixing tm and topicmodels library or WarpLDA from text2vec?

If I am trying to classify 230k text abstracts, which option would be better and more precise when aplying LDA?
0
votes
0answers
19 views

How to find the feature/(data column) that separates each cluster of K-means?

I have a general question on applying k-means clustering on the datasets.. How to find the feature/(data column) that separates each cluster of K-means? may be using scikit-learn in python .. Best ...
0
votes
0answers
74 views

How to derive gradients for softmax function

We have the following feedforward equations: $z_1 = W_1x + b_1$ $a_1 = f(z_1)$ $z_2 = W_2a_1 + b_2$ $a_2 = y^* = softmax(z_2)$ $L(y, y^*) = -\frac{1}{N}\sum_{n \in N} \sum_{i \in C} y_{n,i} \log{...
0
votes
0answers
104 views

Filling 2 different values for missing/NaN columns

I am doing a binary classification problem (TARGET = 0 or 1). My dataset contains some NaN ...
0
votes
0answers
562 views

Value Error: MSLE & CrossVal

I'm trying to run cross validation with mean squared log error with sklearn and getting the following error message: ...
0
votes
0answers
19 views

How to find zone of image?

Hello.! I have been working on a gujrati handwritten dataset to identify character using kNN. i'm not able to find the zone of image like above in python. please help me..!!
0
votes
0answers
18 views

Suggestions on non-linear dimensionality reduction for small, one-hot encoded dataset

I wish to apply non-linear dimensionality reduction on a very small dataset (less than 100 observations). The dataset is very sparse, of approx 20 columns, each containing either 0 or 1. It's the ...
0
votes
0answers
22 views

Can linear classifiers be used at each node of a decision tree instead of the lines parallel to any one of the axes?

I am relatively new to AI/ML. I came across this question while reading some content on ML. Would be of great help if anyone can answer this
0
votes
0answers
387 views

Gan in Keras - You must feed a value for placeholder tensor

i have a problem with the training of my GAN. I get the following error message: ...
0
votes
0answers
56 views

GPS Data Preprocessing Recommandations?

GPS Data Preprocessing I got gps traces of busses which traveled from one place (bus station) to another. This file contains relevant(eg:- Data recorded between the starting bus station and ends ...
0
votes
0answers
195 views

SGD Optimizer NAN Loss

I am working on a regression type problem. When if run to train the model i am facing the following outputs. Is there any problem in my code? I also used adam, it gives numeric loss and ...
0
votes
0answers
259 views

GradCAM heatmap all negative

I've fully trained the VGG16 model on my dataset, resulting in a 97% validation accuracy. I'm using the code from this github: https://github.com/PowerOfCreation/keras-grad-cam but for 2 of my 16 ...
0
votes
0answers
30 views

Dataset creation software

Hello I am looking for a dataset for printed english characters but I am not able to find anything concrete. Is there any software which can generate multiple images from one image. I can build my ...
0
votes
0answers
44 views

Spatial and temporal information processing together (CNN and LSTM)

I have small problem that requires to process both spatial and temporal information. I need to predict vehicle's trajectory based on previous trajectory information and map information. My current ...
0
votes
0answers
19 views

How could a considerable increase in loss leads to an improvement in accuracy?

I'm experimenting with NLP and at the moment, I'm trying to come up with a translator model for converting English sentences to French counterparts. I'm using this dataset (not that it's relevant): ...
0
votes
0answers
480 views

Cat2Vec embedding a categorical value columns with respect to multiple y's

I try to do some embeddings on categorical columns using Keras. Here is the code: ...
0
votes
0answers
21 views

Will it be more computationally expensive to have multipl 2d tensors or 1 3d tensor

Odd question but I am busy creating a Genetic Algorithm that optimizes the weights on a Neural Network instead of using good old fashion 1st-order optimization (Gradient/Adam) What I have is x as a ...
0
votes
0answers
122 views

Image Classification approach for Text images

Let me introduce myself as a beginner to machine learning problems. We are trying to build a system to classify images of text-data like bills, orders, bank-statements etc. We started with the image ...
0
votes
0answers
39 views

Same coefficient in multivariate regression with dummy variables

Hello Data Science community, I have a model with 1 quantitative variable (y) and 2 categorical variables. In order to work with the categorical variables I have created dummy variables (binary) for ...
0
votes
0answers
152 views

Multi Class Text Classification

I am new in deep learning and I am trying to build a classification module which can classify text to one of 9 classes and then use the result of the classification to classify them to another set of ...
0
votes
0answers
16 views

searching for vocabulary for machine translation

Searching for DE-EN vocabulary, that I can use in my machine translation. It should consist of DE-EN phrases, words, sentences etc. Got one from here http://www.manythings.org/anki/ , but searching ...
0
votes
0answers
25 views

Bayesian test for classification problems?

I am using two classification algorithms in Weka i.e. Logistic Regression and Naive Bayes and want to know which algorithm has better performance? I need a statistical test like Bayesian, so which ...
0
votes
0answers
48 views

Error while writing perceptron algorithm binary classifier

I am a beginner and I am designing an binary classifier using Perceptron algorithm using FASHION-MNIST dataset. While designing the same I have written the following code: ...
0
votes
0answers
2k views

TypeError: unhashable type: 'numpy.ndarray''

When I tried to execute the below code for epoch in range(training_epochs): sess.run(training_step, feed_dict={x:train_x,y:train_y}) the following error is ...
0
votes
0answers
26 views

Linear Regression Error in feature matrix step

I'm trying to code the design function used in linear regression using numpy and I get this error: Traceback (most recent call last): File "C:\Users\visha\AppData\Local\Continuum\anaconda3\lib\...
0
votes
0answers
469 views

What is the State-of-the-Art open source Voice Cloning tool right now?

I would like to clone a voice as precisely as possible. Lately, impressive models have been released that only need about 10 s of voice input (cf. https://github.com/CorentinJ/Real-Time-Voice-Cloning),...
0
votes
0answers
52 views

LSTM forcasting: time series as input and a unique value for each as output

I am sorry for the mistakes I will make in this post, I'm new to deep learning ^^' I am trying to build an LSTM model that can help me predict some unique value according to time series indices and ...
0
votes
0answers
50 views

How to read binary video format in HDFS using pyspark?

We want to work on detection of pedestrians in a video using ML algorithm.But the video is in the HDFS file system.How can we read the binary video file format from HDFS using spark? Please help me ...
0
votes
0answers
39 views

Classify the input set into categories based on pre-defined rule set

I'm trying to solve a problem where there are 2 input files given, Input 1: A set of strings in the format. All the strings start with "A". A-B-C-D A-B-C-3 A-X-Y-Z-4 A-X-5 A-X-P-Q-R A-X-P-Q-S A-M-9-...
0
votes
0answers
116 views

How to create an image with pixel values of another image?

I have the following situation: I have an image file with each pixel having a specific value. Now I want to rearrange and distribute these pixel values so that the result image looks similar to a set ...
0
votes
0answers
838 views

How to determine a shape of input and output nodes in graph. (Tensorflow C++)

At first, I tried to implement the following pipeline: 1a) I converted the model from keras (.hdf5) to tensorflow (.pb) and saved using the ...
0
votes
0answers
22 views

How to obtain the predictions of SVM model on single input?

So, I am trying to build a Spam detection model. It is trained on a dataset consisting of about 3500 messages. I used SVM to build a model. But, if I now wish to find out whether a message is spam or ...
0
votes
0answers
53 views

Linear/Logistic Regression for unknown values or how to get a good prior for new coefficients

Suppose, we model the probability of making holidays by country and town. The input data are people and how many people actually made holiday in that particular town: ...
0
votes
0answers
80 views

how should I train a model with transformed parameters

Lets say that we have the following model: $y = sigmoid(w1)*x1 + w2*x3 + w3*x3$ and we would like to fit it in a dataset $(xn, yn)$. How can we do this? (e.g using gradient descent? Also, what could ...
0
votes
0answers
30 views

Are application assignments in Datascience common practice?

this might seem off topic, but I hope this question will be tolerated. I was recently asked to help a friend with an assignment in the process of applying for a new job as data scientist. And ...
0
votes
0answers
20 views

Machine Learning alternative for hashing

Is there a Machine Learning technique that can used to detect the slightest change in data? I know this can be done using a hash but I was just wondering if there is any machine learning technique out ...
0
votes
0answers
31 views

K fold In python

I have problem when using fold with python only one index of one fold shown in y_test ? my data contain 4240 records and only 424 shown in y_test and ...
0
votes
0answers
20 views

Create labels or annotation from two color images

I have two categories of images to use in my deep learning model. The firs category is aerial images that contain roads (such as road-1.jpg). The second category is two color images that contains road ...
0
votes
0answers
29 views

Why do the training curve fall sharp suddenly?

I am training a CNN classifier on a binary balanced dataset. The dataset has 4500 numbers of tweet data along with the class of the tweet. During training, I am applying, GLOVE embedding of 300 ...
0
votes
0answers
40 views

Overfit model after introduce dropout=0.5

I am facing a problem where my validation loss stagnates after 20 epochs. The training loss keep reducing which makes my model overfit. I have tried dropout with a value of 0.5 but there is no change ...
0
votes
0answers
41 views

CNN model overfitting to a Color, not learning edges

I've been working on this binary classifier which predicts if a certain type of battery is in the live webcam feed or not. The problem I am facing is that my CNN model predicts any 'orange object' in ...
0
votes
0answers
94 views

Can I update my model using partial_fit after training my model using fit?

I have trained my model using MLPClassifier using fit method and saving in pickle object for the first time. ...
0
votes
0answers
52 views

LSTM architecture for multivariate time series

For a multivariate time series analysis, which of the following LSTM architectures would work better and why? 1) Having two independent LSTM layers (one for the time series variable and one for the ...
0
votes
0answers
30 views

Should I load my model pkl object every time when I predict?

I am predicting the data in real time , when I hit the url it should predict but I should not load my model again and again . Can someone help to optimize the code ? Can I load globally or how can I ...
0
votes
0answers
24 views

Error while using NLTK/ How should I read paragraph using NLTK?

I am a total newbie. I have a custom text document which is a paragraph. I am trying to read it and display using NLTK. following is my code; ...
0
votes
0answers
16 views

What does sparsely compute mean?

I heard someone say a neural network needs to sparsely compute the output. I get what compute means, I get what a sparse matrix is, but what does sparsely compute mean?

15 30 50 per page
1
117 118
119
120 121
123