Utilizing machine learning techniques has always required choosing hyperparameters. This is true whether one uses a classical technique such as a KNN or very modern neural networks such as Deep Learning. Though in many applications, hyperparameters are chosen by hand, automated methods have become increasingly more common. These automated methods have become collectively known as automated machine learning, or AutoML. Several automated selection algorithms have shown similar or improved performance over state-of-the-art methods. This breakthrough has led to the development of cloud-based services like Google AutoML, which is based on Deep Learning and is widely considered to be the industry leader in AutoML services. Extreme Learning Machines (ELMs) use a fundamentally different type of neural architecture, producing better results at a significantly discounted computational cost. We benchmark the Extreme AutoML technology against Google's AutoML using several popular classification data sets from the University of California at Irvine's (UCI) repository, and several other data sets, observing significant advantages for Extreme AutoML in accuracy, Jaccard Indices, the variance of Jaccard Indices across classes (i.e. class variance) and training times.

Many of our everyday routines and schedules are now handled automatically by robots, digital assistants, and tools as technology advances. These tools aid in the simplification of job procedures and enable us to accomplish a great deal in a short period of time. Adoption of AI in various sectors of the economy has significantly aided societal growth and development. We are all aware of the traditional approach to building AI models, which entails several hours of coding and the requirement for systems with significant computing power. We now have AI tools that allow us to create AI models without writing a single line of code.

Tabular data is omnipresent nowadays and can provide us with meaningful insights into both business and engineering problems. A common way of extracting these insights is by applying machine learning (ML) techniques to this data. The process of applying ML to a dataset consists of various steps, e.g., data preprocessing, feature engineering, and hyper-parameter optimisation, with each of these steps often being a time consuming trial and error process in and of themselves. Additionally, one needs to be an expert in the domain of ML in order to be efficient and effective at each of these steps. It can take quite some time for an organisation to either find these domain experts externally, or grow this expertise in-house.

In this tutorial, I'll show you how to create a single label classification model in Google AutoML. We'll be using a dataset of AI-generated faces from generated.photos. We'll be training our algorithm to determine whether a face is male or female. After that, we'll deploy our model to the cloud AND create the web browser version of the algorithm. First let's take a look at the data we'll be classifying (you can download it here).