Blog

Artificial Neural Networks (ANNs) have become a very popular Machine Learning model architecture; www.marketsandmarkets.com predicts a 20.5% Compound Annual Growth Rate (CAGR) over the coming years:

Factors contributing to ANN growth include:

Big Data - ANNs have the ability to use very large input data sets for model training and the amount of data available is growing rapidly
Research and Development - the number of ANN published research papers is growing rapidly as are new applications
Model Variations - there are a large number of ANN variations available, including: Convolutional Neural Networks, Deep Learning, Generative Adversarial Networks, Long Short-Term Memory, Recurrent Neural Networks, Reinforcement Learning, Transformer Neural Networks
Flexibility - ANNs can be configured using a number of modeling process hyperparameters, including: data features, network graph architectures, training learning rate, model training times to control factors such as the Bias-Variance Tradeoff
Hardware Processing Acceleration - technologies such as Graphics Processing Units, Tensor Processing Units, and other AI Accelerators can be used to reduce model training times

In effect, ANNs have become a virtual ‘Swiss Army Knife’ of Machine Learning.

The Science of Machine Learning started as a single blog post on my personal website www.donkcowan.com. It grew to the point where editing and managing it as a single post became impractical. I considered converting the content to a book, however creating a separate website seemed like the better approach as it offers easy content creation, updating and linking.

The website provides an overview of major Machine Learning science concepts, techniques, approaches and more. Each topic is covered on a separate web page and includes references for additional information.

Machine Learning is an amazing combination of Mathematics, Data Science, and Computer Science, including: