# All Questions

20,281 questions
Filter by
Sorted by
Tagged with
5 views

### Is it feasable to “predict” 2d (~2x20 array) output using a CNN

I'm trying to generate a "beatmap" (from osu!mania) based on an audio file. To do this, I've applied fast fourier transform (this can change to Mel-frequency cepstrum, but that's not super relevant) ...
6 views

### Types of Machine Learning/Data Analysis

I am looking for a framework or chart that classifies all the different types of data analysis/machine learning. I want to use this classification to organize my knowledge/areas to learn. Examples of ...
6 views

### Error using msmFit in R

I am trying to analyze a time series data using the MS model with R. I wrote the following codes and then got an error at the last line: ...
12 views

### Neural Network from scratch: cost increasing over epochs

I'm trying to design a neural network from scratch. After training my neural network, I make a plot of the cost vs epochs, which I would expect to decrease throughout the runtime of the NN training, ...
9 views

### Am I overfitting my random forest model (more information in description)?

First off, sorry if this a novice question! Relatively new to all this stuff. Posted this in Stack Overflow and someone sent me here! Hope it's the right place. Anyway, I'm working with 22 datasets ...
7 views

### Trying to determine if inputs are integers or floating point using an ANN

i am new to machine learning and just getting started on keras. One of the things i am trying to do is feed a neural network with two inputs (numbers) and find out if it is an integer or a float. ...
8 views

### What are the tradeoffs between Bayesian Deep Learning and Deep Gaussain Processes?

I understand the differences between Deep Gaussian Processes(DGPs) and Bayesian Deep Learning(BDL): DGPs are essentially feed-forward neural networks where each node is a Gaussian Processes, which BDL ...
11 views

### Python Keras model performs much worse than R Keras model

I got this R Keras model from GitHub that performs really well. GitHub repo ...
5 views

### Autoencoder clustering with a small dataset

I have a dataset which is relatively small (less than a 1000 samples). I run an autoencoder on a training set, and then check the reconstruction error on a validation set and stop training before it ...
11 views

### Clustering Small Text Descriptions

Im presented with a unique text classification problem. Im given a list of descriptions each containing 3-8 words. I know that there are some descriptions that are nearly the same, but the majority ...
6 views

### Which technique was semantic similarity improved from

Am looking for a material that explains how semantic similarity began,which problem leads to the application of semantic similarity method and proper explanation of it's algorithm.
3 views

### Fastest batch perspective transform for image augmentation

I need to do some augmentation for my training images for a neural networks. The problem is that even when loading batches in parallel, the augmentation is taking longer to perform than the network ...
6 views

### Wavelet transform to identify 'meaningful' data changes

Can I use the wavelet transform to find the 'meaningful' changes in a series of 1d data? For example I have a series of integers representing angles of line segments. The majority of these values are ...
17 views

### Which Machine Learning methods would be good for a beginner-level Data Science project for described dataset? [on hold]

I want to do my first beginner-level project regarding Data Science. I picked my data set which is described below. I want to make a Python script which will make some predictions on our data set ...
18 views

### Can a data scientist analyze [on hold]

A data scientist, unlike data analyst, can make predictions which help businesses make accurate decisions. They can do nearly all the tasks a data analyst can do as they too are proficient in ...
3 views

### Plotly Bar Graph Color Scale [migrated]

I'm trying to keep a bar graph values on the same color scale - for example: ...
8 views

### Question mark on Correlation Matrix with RapidMiner

I'm using RapidMiner to evaluate correlation between attribute in my dataset. The problem is that a lot of values appear with '?'. Someone can help me? This is a sample of data
15 views

### Are there any graph embedding algorithms like this already?

I wrote an algorithm for generating node embeddings based on the graph's topology. Most of the explanation is done in the readme file and the examples. The question is: Am I reinventing the wheel? ...
7 views

### Finding image dataset of color-blindness charts [on hold]

I had an idea to train a CNN to classify numbers seen on color-blindness charts like the one seen below. I have Google for such dataset but did not find anything. How should I approach this?
11 views

### Why the first prediction of neural network in PyTorch is slower than following predictions?

So I have ResNet50 trained to classify images. For each prediction I track the time needed for it (input and model are moved to GPU): ...
14 views

### What are current state-of-the-art data science models of forecasting (e.g., weather, disease outbreaks, polls) [on hold]

I'm currently working on a forecasting model that would predict future sentiments (display on a map) from spatio (locations) - temporal (timestamps) data, combined with sociodemographic, textual (news,...
7 views

### Setting a threshold for tfidf

Let's say I have streaming textual data coming in. I run named entity recognition software to capture the entities, then I score them using tf-idf. Tf-idf scores are unbounded positively. How can I ...
19 views

### Managing NaN in target variables (testing)

Please can someone advise me on how to handle NaN in my target variables set? I've tried a variety of things but none is working. Here's what I've tried: Imputing zeros (0) in Y_test Replacing NaN ...
12 views

### Merge columns of coordinates and construct sequence

I have to following data frame. ...
4 views

### Which is best FaceNet or dlib_face_recognition_resnet_model_v1?

I am newbie in face recognition related things... As far i observed dlib's frontal_face_detectoris widely used to find the faces in an image and after that, to ...
24 views

### Not able to connect to GPU on Google Colab

I'm trying to use tensorflow with a GPU on Google Colab. I followed the steps listed at https://www.tensorflow.org/install/gpu I confirmed that gpu is visible and CUDA is installed with the ...
11 views

### How to obtain the word vectors optimally

I have a list of strings as shown sent_list = ["Carrefour is in France", "Apple pie is delicious", "Amazon has just delivered", ...] My code to get word ...
9 views

### How to build in symmetry of inputs into a Deep Neural Network?

I have a Deep Neural Network that takes $n$ inputs $X = [X_1, \ldots, X_n]^T$ and gives $n$ ouputs $Y = [Y_1, \ldots, Y_n]^T$. Normally, I can just do a standard deep neural network with a few fully ...
5 views

### Differnt loglikelihood values in RandomSearch/GridSearch and LDA . How to synchronize them?

I am doing a sensitivity analysis for some lda parameters in python. This is what I want to do: -Do RandomSearch to find optimal Parameters and therefore the optimal lda model. As Validation measure ...
21 views

### How could I improve my FB Prophet forecast?

I've got 1325 days of revenue data and when plotting the components it makes 100% sense from a domain expert point of view, so the model is capturing the variations quite well (or it seems it does...)....
16 views

### Build a model to classify given string/text input

I need to build ML/NN model to classify/predict a given string pattern. Sample training data looks as shown in the image. Input will be the string in the column "Id Number", i need to tell to which ...
3 views

### m = rating.pivot_table(index=['user_name'], columns=['site'], values = 'rating') [on hold]

m = rating.pivot_table(index=['user_name'], columns=['site'], values = 'rating') I wrote this command, and it shows this error. I do not know what's wrong can any ...
13 views

### Statistical loss function for categorical distributions

For training an autoencoder model whose outputs (and inputs) are parameters from a categorical distribution $[q_1, q_2, \ldots, q_n]$, I have to define a proper loss function measuring the distance ...
8 views

### Multivariate survival analysis on R?

I’m doing a project where I need to carry out a multivariate survival analysis in R. The usual method is to use a Cox proportional hazards model but in this case, the proportional hazards assumption ...
29 views

### Prediction error without having a true value

Quick summary about the problem: we are trying to deploy our regression model, where the clients require "individual prediction error". Since we're predicting something unknown in advance, we can't ...
6 views

### How to get a percentage of similarities of new data added based on model trained using a huge training set in machine learning

I need to find similarities in newly added data using machine learning. We have a huge data set with more than 200 000 rows having following information: Name D.O.B City (From predefined list) Phone ...
14 views

### Variability in CNN test results

I'm trying to do some time series analysis on 1-minute forex data using a CNN. I'm new to deep learning and just getting started in building a model. So this is probably a very basic question, but I'...
12 views

### what is the difference between these NLP terms latent,syntatic, semantic and context of words in sentence? [on hold]

what are these terms used in natural language processing used for : latent,syntactic, semantic and context? they all look similar to me .
17 views

### How to handle multi-label feature for binary classification problem?

I have dataset like : ...
46 views

### How to handle addresses of the restaurants to feed the data-set in the ML model?

I have data from different restaurants which have also address of the restaurants now I want to predict the food delivery timing based on the given data, now the restaurant address is one of the ...
6 views

### should we apply he Same normalization to New Data as well for prediction [on hold]

I came across the post. Should we apply normalization to test data as well?
19 views

### Unsupervised image classification?

Does this exist? What algorithm or combinations of algorithms would be able to classify images without supervision? For example if you have many pictures of cats and dogs, then without being trained ...
13 views

### Categorial Encoding with different cardinality

I have some user data for his data activities. Some examples of the columns are : Activity : ex. youtbube , viber, whatsapp etc etc. Cardinality > 1000 Region : Area identifier Cardinality > 10000 ...
9 views

### Gaussian process regression for large dimensional input space

I am working for Gaussian process (GP) regression $y=f(\mathbf{x})+\epsilon$ with $\mathbf{x}\in \mathbb{R}^D$ and $D$ can be as large as few 100. I have attempted with the GPML toolbox and the exact ...
9 views

### Can feature representation acquired by a same model but trained on different corpus be used on the same classification model?

For example, if I wanna do document classification with doc2vec embeddings, first I train the training set to get doc2vec embeddings, and fit the embeddings to a classification model; later on when I ...
6 views

### Weather Forecasting: CNN-LSTM or ConvLSTM?

I am trying to develop a weather forecast model where satellite images (temperature, velocity field etc) are stacked over time. Since the prediction model needs to analyze both spatial features and ...
2 views

### How to increase spark rpc maxSize value [migrated]

I am getting this error while running keras model with eliphas_estimator on databricks cluster. can anyone tell me in detail how to resolve this error, i have already seen some documentations but i ...
12 views

### Calculation of Neural network biases in backpropagation

While learning neural networks I've found a basic Python working example to play with. It has 3 input nodes, 4 nodes in a hidden layer, 1 output node. 5 data sets for training. The initial code is ...
I am trying to replicate (a way smaller version) of the AlphaGo Zero system. However, in the network model, I am having a problem. The loss function I am supposed to implement is the following: l = ...