Maksim Khaitovich

Maksim Khaitovich has asked 15 questions and find answers to 25 problems.

Stats

About

Analytics Manger at Kearney.

Applying AI and ML for business problems and managerial decision making. My main areas of interest are artificial neural networks, data science, decision science and operations research

Maksim Khaitovich questions

Keras - method on_batch_end is slow but only callback I have is checkpoint
Pandas + scikit-learn K-means not working properly - treats all of dataframe rows as one big multi-dimensional example
R - select only factor columns of dataframe
Adding sparse matrix from CountVectorizer into dataframe with complimentary information for classifier - keep it in sparse format
Audio spectrum extraction from audio file by python
TensorFlow - GradientDescentOptimizer - are we actually finding global optimum?
scikit-learn, linearsvc - how to get support vectors from the trained SVM?
Ensemble of different kinds of regressors using scikit-learn (or any other python framework)
TensorFlow - introducing both L2 regularization and dropout into the network. Does it makes any sense?
TensorFlow - regularization with L2 loss, how to apply to all weights, not just last one?

Maksim Khaitovich answers

How could I use batch normalization in TensorFlow?
Extract Dates and events associated with the date from Text corpus
How to plot SVC classification for an unbalanced dataset with scikit-learn and matplotlib?
How to deploy machine learning algorithm in production environment?
Deep learning Udacity course: Prob 2 assignment 1 (notMNIST)
TensorFlow: Adding Class to Pre-trained Inception Model & Outputting Full Image Hierarchy
Ensemble of different kinds of regressors using scikit-learn (or any other python framework)
TensorFlow - introducing both L2 regularization and dropout into the network. Does it makes any sense?
sklearn - Predict each class's probability
Can a neural network be trained while it changes in size?