Category "machine-learning"

Compute Similarity(percentage) between two Matrix/Array

How to compute similarity(percentage) between two matrix/arrays. or find the closest array/matrix to a given array, on the basis of how similar their data value

How to configure the Keras Optimizer and Learning rate using config.yaml file?

I have defined few parameters in my config.yaml like as below. params: epochs: 10 batch_size: 128 num_classes: 10 loss_function: sparse_categorical_cros

Sklearn Pipeline with KernelExplainer and data to predict as DataFrame leads to error

I want to calculate shap values from a sklearn pipeline with a preprocessor and a model. When i do it with the code below I get 0 for all shape_values def creat

Negative BIC values for GaussianMixture in scikit-learn (sklearn)

In scikit-learn, the GaussianMixture object has the method bic(X) that implements the Bayesian Information Criterion to choose the number of components that bet

KeyError: 'initialized_diffuse'

I'm getting a keyerror 'initialized_diffuse' while calling the following API, probably after joblib.load(). import joblib .......... @routes.route("/forecast",

Why the sum "value" isn't equal to the number of "samples" in scikit-learn RandomForestClassifier?

I built a random forest by RandomForestClassifier and plot the decision trees. What does the parameter "value" (pointed by red arrows) mean? And why the sum of

Custom GRU model (OGRU)

I want to customise the GRU-RNN cell from tensorflow. But i dont know which function i need to change from standart GRU from tensorflow. i want to modify GRU ce

Hardware for Machine Learning / Deep Learning

I want to build a new computer for Data Science purposes. What do you think about this hardware: https://www.ldlc.com/configurateur-pc/23fe088422141bb69274a13ca

GlobalAveragePooling1D equivalence with Lambda Layer

Is the GlobalAveragePooling1D Layer the same like calculating the mean with a custom Lambda Layer? The data is temporal, so x has shape (batch, time, features)

Assigning custom weights to embedding layer in PyTorch

Does PyTorch's nn.Embedding support manually setting the embedding weights for only specific values? I know I could set the weights of the entire embedding laye

Decision tree regression producing multiple lines

I'm trying to make a single variable regression using decision tree regression. However when I'm plotting the results. Multiple lines show in the plot just like

Instantiate Keras model with some weights before training

I have Keras model: pre-trained CV model + a few added layers on top I would want to be able to do model.predict before model.fit Q: how do I instantiate model

Pytorch RuntimeError: CUDA out of memory with a huge amount of free memory

While training the model, I encountered the following problem: RuntimeError: CUDA out of memory. Tried to allocate 304.00 MiB (GPU 0; 8.00 GiB total capacity; 1

How to quantify privacy, when using homomorphic encryption?

How can you measure how secure or private the new variables are relative to the real (actual) variables. I want to compare homomorphic encryption and differenti

Classifying the order of classes rather than the classes themselves

I'm currently tackling a classification problem that needs prediction of the order of objects in a sequence, but not the object class itself. I've spent quite s

Extracting education from Text data

I have bunch of text data describing people's eduation. I have already done some basic NLP processing to those text data. An example would be this : XXX receive

Semantic segmentation with detectron2

I used Detectron2 to train a custom model with Instance Segmentation and worked well. There are several Tutorials on google colab with Detectron2 using Instance

Activation function on the hidden layers for Regression models in neural networks

I am trying to predict a single output value,y, using two input features. I read that regression models usually don't use any activation function, and even when

vowpal wabbit java: get raw predictions

I am using Java API of vowpal wabbit to get predictions. I need raw prediction (same as -r output.txt) but I couldn't find any such method in VWMulticlassLearne

Handwritten digit recognition without deep learning techniques

I have a project to hand in which requires me to develop a program in python which would recognise handwritten numbers given in the form of image(i imagine the