machine learning

Our rating: ★★★★☆

[amazon_link asins=’0387310738′ template=’ProductAd’ store=’ATVPDKIKX0DER’ marketplace=’US’ link_id=’3cd0fb47-c068-11e7-bf0d-457237168d3c’]

This book is one of my first Data Science books I bought and one of the books I personally use most often. In this Pattern Recognition and Machine Learning review, I will give you my opinion on this book. Most of the core concepts of Data Science are discussed in this book, ranging from Stochastic Gradient Descent to Neural Networks and are explained in clear and understandable English. Some of the courses I followed were hard to follow, but most of the times, I could look up related material in this book which explained it in simple text with many examples. There are also plenty of exercises to help you through a topic and it builds up nicely. It explains nearly all pattern recognition or machine learning concepts and offers an comprehensive introduction to the fields of computer science, data mining and computer vision. Besides that, it sheds also lights on topics like probability theory in which many probability distributions and graphical models are explained. The great thing is that no previous knowledge of pattern recognition is assumed. So for beginners, advanced undergraduates or first year PhD students, students as well as researchers, researchers and practitioners, this book is an absolutely must-have. For more advanced Data Scientist, this book is great reference material. Make sure to buy this book now and add it to your collection!

[amazon_textlink asin=’0387310738′ text=’Learn more here!’ template=’ProductLink’ store=’ATVPDKIKX0DER’ marketplace=’US’ link_id=’2c85f4dd-c081-11e7-bde7-654fa342e72f’]

MLPs (Multi-Layer Perceptrons) are great for many classification and regression tasks. However, it is hard for MLPs to do classification and regression on sequences. In this Python deep learning tutorial, a GRU is implemented in TensorFlow. Tensorflow is one of the many Python Deep Learning libraries.

By the way, another great article on Machine Learning is this article on Machine Learning fraud detection. If you are interested in another article on RNNs, you should definitely read this article on the Elman RNN.

(more…)

You want to build your own Tic-Tac-Toe opponent? Then you need to read further! In the Tic-Tac-AI series, I will present a couple of Artificial Intelligence algorithms implemented as Tic-Tac-Toe opponent. In this first article, I will introduce a method called Forward Sampling which is capable of not losing any game of Tic-Tac-Toe!

(more…)

How can we use machine learning to predict stockprices? In this tutorial we will make Python scripts for doing sentiment analysis on Tweets and it is explained how to use it for making predictions.

As an example, suppose we had €1000,- at the first of January of 2014 and suppose we could use the algorithm which is described in this tutorial. Then it would generate €2901,- in total on the 22th of February, 2017! The total amount of money (cash + investments) is shown in the next figure:

Money.

Despite the patience you need to have, it will be worth the waiting time eventually. As mentioned in [1], moods in tweets are a good indication of the movement of closing prices on a stock market. In this article, we will only predict how positive or how negative a tweet is. But it turns out that this is giving predictive signals which is accurate enough for our purposes.

Looking for new interesting investments idea? Check out our Crypto Advisor service!

(more…)

There are lots of Python packages available on the internet. The aim of this post is to give you an overview of scientifically oriented Python packages, sorted per topic. The list will be updated regularly. If you have any recommendations, feel free to give your addition in the comments!

(more…)