All Questions

0
votes
0answers
9 views

SCIKIT-LEARN export results

I made a classifier with sci-kit learn. How do I deploy it on data? I see the results but I want to see the account data (in excel) that labeled it. For example I want to open an excel sheet and have ...
0
votes
0answers
7 views

How to Do Label Smoothing when Legal Classes Change

Label smoothing often helps accuracy, but I'm modeling a game where only some of the possible move outputs can be legal at a time, so I think it makes sense to smooth the labels among currently legal ...
0
votes
1answer
9 views

How to compare and find common values from different columns in same dataframe?

I would like to compare two columns and find common values sets in each column, then output the rows with the common values. Let's say I have a dataframe with: no.(col1) | Username (col2) | Referral(...
1
vote
1answer
13 views

How does recommendation by matrix factorization deal with new movies / users?

Assume you have the ratings of $n$ users for $m$ movies in a matrix $R \in \mathbb{R}^{n \times m}$. You compute a representation $$R = U \times \Sigma \times V$$ by initializing $u_i, v_j \forall i ...
0
votes
0answers
6 views

Autoencoder not overfitting data after large number of epochs and small number of samples

I am training a deep autoeocoder on numerical data, with python jupyter notebook. I have 17 samples, each with 534 values, and my auto encoder has all layers to 534, but even after 5,000 epochs, the ...
1
vote
2answers
15 views

Supervised learning approach - creating my own labels

****Scenario** - I have data that does not have labels but i can create a function to label the data based on behavior and deploy the model so i don't have to keep labeling the data. Is this ...
0
votes
0answers
11 views

Creating artificial blurred image to train neural network for super resolution

I would like to create blurred images from images obtained from large pdf with the intention of creating a training data set. I would like to create the blur as shown in the uploaded picture. Which ...
0
votes
1answer
8 views

How to efficiently iterate a supervised model over the Cartesian product of very large number of records?

The problem: Two large databases, with ~1M records each, "old customer data" and "new customer data". The data came from different sources and was ingested at different times, so there are many ...
0
votes
0answers
5 views

Any there databases with native support for applying a NN model to produce search rankings?

The Situation: I have a simple neural net with an input vector that consists of the euclidean distance between the attributes of two cars. (For example the attributes would include wheel size, car ...
0
votes
1answer
6 views

Do word embeddings help with out of vocab tokens?

I am performing sentiment analysis on a custom dataset of text with Keras but am a little confused about word embeddings. I have been able to train an "Embedding" layer and have also learned to load ...
0
votes
0answers
4 views

Analyse performance of NN

Matlab's train command internally splits the dataset into train,val,test: ...
0
votes
0answers
13 views

Regularization loss - Why is that important to get unique weights solution

There's something that is bothering me in Regularization. There is one bug with the loss function when I just use for e.g. a multi-class SVM loss. Suppose that we have a dataset and a set of ...
0
votes
0answers
13 views

Time Series Forecasting with RNNs

I'm attempting to develop a recurrent model to forecast the value one step into the future (i.e., $x_{t+1}$), given its history $(x_{t-h},\cdots,x_{t})$, where $h$ is a fixed hyperparameter for the ...
1
vote
1answer
12 views

How to cache GridSearchCV optimizer result in Google Colab?

I have to execute GridSearchCV() cell every time I reload the page and it takes a lot of time. Is there a caching mechanism which stores the GridSearchCV result so that I can use it without executing ...
0
votes
1answer
18 views

in TensorFlow 2.0, what is the different between LSTM and LSTMCell objects?

I am trying to implement an RNN in TensorFlow 2.0 (beta1). Looking at the layer functions (inherited from Keras) I found: tf.keras.layers.LSTM and ...
0
votes
0answers
21 views

How to determine percent contribution to classification in logistic regression?

I'm trying to understand the contribution of each feature towards a specific classification. Let's say I have clients as my data and their features are income, debt and age. We're trying to predict ...
1
vote
1answer
8 views

Is Faster RCNN the same thing as VGG-16, RESNET-50, etc… or not?

My understanding is that Faster RCNN is an architecture for performing object detection. It finds objects in an image and classifies them. My understanding is also that VGG-16, RESNET-50, etc... also ...
2
votes
2answers
12 views

Does partial transfer learning require a lot of computer power?

I want to be sure my understanding of the problem is correct. I want to do image classification and current state of the art in my field is achieved by transfer learning with VGG16. Since image on ...
0
votes
0answers
13 views

Is there any formula that estimates the training time of a CNN?

Is there any formula which estimates the training time of a CNN? (with respect to the number of layers, the size of the dataset ...
0
votes
0answers
6 views

Monte Carlo Dropout as Uncertainty predection

I am pretty new to Python and this board so I am not sure, if I am at the right place for my question since it doesn't include any code. If not so, please give my a hint for a better way/place to ask. ...
0
votes
0answers
13 views

Getting validation loss and training loss constants across epochs

I have the following model, where validation loss and training loss is constant. I am processing twitter posts for sentiment analysis. ...
1
vote
2answers
26 views

Neural network got a lucky guess. Can it be trusted?

Say you come across a loss curve as shown below. At which loss should you trust the model? The initial lucky guess or after it has stabilized? And more importantly, why?
0
votes
0answers
3 views

PREDICTIONS ON ODI MATCHES [on hold]

using the following data I have attached below, how can I predict who will win in the next ODI match? I want to consider the data of last 5 years only i.e.2011 to 2016. https://www.kaggle.com/jaykay12/...
0
votes
1answer
12 views

LeCun paper on deeplearning (Nature, 2015)

As I was reading Y. LeCun's paper on Deep Learning (Nature, vol. 521, 2015), I came across a figure (the 1st one in the paper) which was associated to the backward pass during backpropagation through ...
0
votes
0answers
8 views

General Process for new project

Often when i get a new project in machine learning the client always ask me either to do a particular task like a prediction for one thing or give me data and ask me to find what i can do with it. i'...
0
votes
2answers
17 views

Classifying whether a chess board square contains a piece or not?

I have an image of a chessboard which I segment into its constituent 64 squares. I want to construct a binary classifier which can detect which square contains a piece or not. I know how to do this ...
0
votes
0answers
12 views

characteristics of time-series datasets

I am working on two different datasets, one of them is a simulated dataset and the other is a real-world dataset. My understanding of RNNs was that they work well with sequential data where a ...
0
votes
0answers
12 views

While reading the pages of a PDF file using Python, I get the following error. There are 300 pages in pdf file

CalledProcessError: Command '['java', '-Dfile.encoding=UTF8', '-jar', 'C:\Users\105051884\AppData\Local\Continuum\anaconda3\lib\site- packages\tabula\tabula-1.0....
0
votes
0answers
15 views

Input contains NaN, infinity or a value too large for dtype('float32') [on hold]

The data set which I am using to predict y_pred does not contain any nan value. Don't know what to do.
0
votes
0answers
2 views

Stained glass extension GAN

I am looking for image extension GAN with support of pattern drawing/extending to a desired image size. And photo as an argument to generate corresponding result. Trained on: Areay of photos of ...
0
votes
0answers
4 views

is “choosing a Q” in chapter 2 in the deep learning book an actual step in eigendecomposition?

eigendecomposition or sometimes spectral decomposition is the factorization of a matrix into a canonical form chapter 2 in the deep learning book says If any two or more eigenvectors share the ...
0
votes
0answers
13 views

Precision of quantized MobileNet v1 224 on CPU and Edge TPU

I am using a quantized MobileNet model for inference tests. I use an Coral Edge TPU and my CPU. For the Edge TPU I use the class ClassificationEngine. For the CPU I use the tensorflow lite interpreter....
0
votes
0answers
5 views

Application of Varitiational Auto Encoders in improving the generalizability of classifiers when there is limited amount of data?

Is there any prior work on the above topic? Currently, I am working on Domain Adversarial Neural Networks and merging it with VAE to improve generalizability and transfer learning. I could not find ...
1
vote
0answers
27 views

I have time series data for months i need to forecast for next 12 months

I have graph like this for that data. When I make adfuller test: ...
0
votes
0answers
14 views

How to utilize dictionary data set for text classification?

I have a dataset similar to newsgroup20 for classification. With the training dataset, I have a dictionary data set that explains some jargons in the training dataset. These both are different data ...
0
votes
0answers
6 views

How to compare genetic profiles or vcf files in Python?

I am wondered how I will compare different vcf files which contain genetic profile in Python? Each vcf file contains profile for a single entity/animal/human etc. I can read each vcf file into ...
0
votes
1answer
34 views

Building resume classifier based on keywords, what would be the steps & what are features and target in this case?

I went through this, as I have a similar requirement (at least what I think, correct me if wrong) of classifying resumes(.doc files) based on the profiles. I have a ...
1
vote
0answers
17 views

MCMC for finding Bayesian Neural Network

Is someone familiar with such an approach: Suppose I want to build a bayesian neural network, with distributions over my parameters instead of point estimates. First I train my network with standard ...
1
vote
0answers
10 views

Expand Seaborn FacetGrid layout horisontally

I have the following code that shows 10 dataframe column values separated by categories PREFERENCE = GOOD and PREFERENCE = BAD. Is it possible to expand the layout horisontally so that instead of 2 ...
1
vote
0answers
14 views

What is the best reference for multi-class SVM?

Can someone suggest some papers about the multi-classification methods by SVM? One against all? A good survey or paper which ...
1
vote
1answer
16 views

Looking for animals dataset for deep learning classification

Do you know any datasets that contain animals and their accurate classifications? I am looking for any dataset that categorizes animals. For example: a dataset with insects, with an image of an ...
0
votes
0answers
7 views

large variance from inverse probability weighting (inverse propensity score)

I heard if the observed data that will be used in the inverse probability weighting method is too small, the estimator based on the weighting will have a large variance. Could you explain why that is ...
0
votes
0answers
10 views

Create 'All' categories and summarize

I have a dataframe with columns as defined below. For each of these variables ...
0
votes
0answers
13 views

PCA giving separated results expected (jupyter sklearn)?

I'm a complete newbie to PCA and I have 3 sets of values which I want to plot with PCA. This is what I am using: ...
0
votes
1answer
16 views

No gradients provided for any variable

I have composed a customized loss function (kl_loss): ...
0
votes
0answers
9 views

Compare large prediction with observed values

I have test scores for a lot of schools and I created a performance index calculated using the last score of a state test. This index is supossed to predict the performance of the school in the next ...
0
votes
0answers
10 views

Script Response Time Anomaly Detection

Currently, I am figuring out how to tackle this problem. I have a dataset of response times for various scripts. These scripts each have multiple steps, of which each step has multiple sub-steps. ...
0
votes
2answers
21 views

How to fit a model to the V-shaped data?

I have a dataset of chromatic and monochromatic galaxy fluxes which looks like inverted V shape as follows: ...

15 30 50 per page