Sebastian Raschka

Michigan State University

Data Scientist and Machine Learning enthusiast with big passion for Python & open source. Author of "Python Machine Learning" book. Tweets at @rasbt.

Troubleshooting Neural Networks: What is Wrong When My Error Increases?

By Sebastian Raschka, Michigan State University on May 13, 2016 in Deep Learning, Neural Networks, Overfitting
An overview of some of the things that could lead to an increased error rate in neural network implementations.
Why Implement Machine Learning Algorithms From Scratch?

By Sebastian Raschka, Michigan State University on May 6, 2016 in Algorithms, Machine Learning
Even with machine learning libraries covering almost any algorithm implementation you could imagine, there are often still good reasons to write your own. Read on to find out what these reasons are.
When Does Deep Learning Work Better Than SVMs or Random Forests®?

By Sebastian Raschka, Michigan State University on April 22, 2016 in Advice, Deep Learning, random forests algorithm, Support Vector Machines, SVM
Some advice on when a deep neural network may or may not outperform Support Vector Machines or Random Forests.

More...12

Top Posts