## An introduction solving differential equations numerically

Geplaatst Geplaatst in Machine Learning, Mathematics

In this blog-post we will have a look at how Differential Equations (DE) can be solved numerically via the Finite Differences method. By solving differential equations we can run simulations of dynamical systems and make predictions about the world. The reason for writing this blog-post is because I am interested in a new type of […]

## Time-Series forecasting with Stochastic Signal Analysis techniques

Geplaatst Geplaatst in Machine Learning, Stochastic signal analysis

1. Introduction In other blog-posts we have seen how we can use Stochastic signal analysis techniques for the classification of time-series and signals, and also how we can use the Wavelet Transform for classification and other Machine Learning related tasks. This blog-post can be seen as an introduction to those blog-posts and explains some of […]

## A guide for using the Wavelet Transform in Machine Learning

1. Introduction In a previous blog-post we have seen how we can use Signal Processing techniques for the classification of time-series and signals. A very short summary of that post is: We can use the Fourier Transform to  transform a signal from its time-domain to its frequency domain. The peaks in the frequency spectrum indicate […]

## Building Recurrent Neural Networks in Tensorflow

Geplaatst

Introduction In the previous blog posts we have seen how we can build Convolutional Neural Networks in Tensorflow and also how we can use Stochastic Signal Analysis techniques to classify signals and time-series. In this blog post, lets have a look and see how we can build Recurrent Neural Networks in Tensorflow and use them to […]

## Machine Learning with Signal Processing Techniques

Geplaatst

Introduction Stochastic Signal Analysis is a field of science concerned with the processing, modification and analysis of (stochastic) signals. Anyone with a background in Physics or Engineering knows to some degree about signal analysis techniques, what these technique are and how they can be used to analyze, model and classify signals. Data Scientists coming from […]

## Using Convolutional Neural Networks to detect features in satellite images

Geplaatst Geplaatst in convolutional neural networks, tensorflow

1. Introduction In the previous blog post we have seen how to build Convolutional Neural Networks (CNN) in Tensorflow, by building various CNN architectures (like LeNet5, AlexNet, VGGNet-16) from scratch and training them on the MNIST, CIFAR-10 and Oxflower17 datasets. It starts to get interesting when you start thinking about the practical applications of CNN […]

## Building Convolutional Neural Networks with Tensorflow

Geplaatst Geplaatst in convolutional neural networks, deep learning, tensorflow

1. Introduction In the past I have mostly written about ‘classical’ Machine Learning, like Naive Bayes classification, Logistic Regression, and the Perceptron algorithm. In the past year I have also worked with Deep Learning techniques, and I would like to share with you how to make and train a Convolutional Neural Network from scratch, using tensorflow. […]

## Classification with Scikit-Learn

Geplaatst Geplaatst in Classification, scikit-learn

update: The code presented in this blog-post is also available in my GitHub repository. update2: I have added sections 2.4 , 3.2 , 3.3.2 and 4 to this blog post, updated the code on GitHub and improved upon some methods.   1. Introduction For python programmers, scikit-learn is one of the best libraries to build […]

## The Perceptron

Geplaatst Geplaatst in Classification, Machine Learning

1. Introduction Most tasks in Machine Learning can be reduced to classification tasks. For example, we have a medical dataset and we want to classify who has diabetes (positive class) and who doesn’t (negative class). We have a dataset from the financial world and want to know which customers will default on their credit (positive […]

## Regression, Logistic Regression and Maximum Entropy part 2 (code + examples)

Geplaatst Geplaatst in Classification, Sentiment Analytics

update: The Python code for Logistic Regression can be forked/cloned from my Git repository. It is also available on PyPi. The relevant information in the blog-posts about Linear and Logistic Regression are also available as a Jupyter Notebook on my Git repository.   Introduction In the previous blog we have seen the theory and mathematics behind the […]