Deep Learning has been getting more and more traction. It focuses on one section of Machine Learning: Artificial Neural Networks. This article explains why Deep Learning is a game-changer in analytics, when to use Deep Learning, and how visual analytics allows business analysts to leverage the analytic models built by a (citizen) data scientist.
Deep Learning is the modern buzzword for Artificial Neural Networks, one of many concepts in Machine Learning that is used to build analytics models. A neural network works similarly to a human brain. You get non-linear interactions as input and transfer them to output. Neural networks leverage continuous learning and increasing knowledge in computational nodes between input and output. A neural network is a supervised algorithm in most cases, which uses historical data sets to learn parameters to predict outputs of future events (i.e. for cross-selling or fraud detection). Unsupervised Neural Networks can be used to find new patterns and anomalies. In some cases, it makes sense to combine supervised and unsupervised algorithms.
Neural Networks have been used in research for many decades and include various sophisticated concepts like Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Autoencoders. However, today’s powerful and elastic computing infrastructure in combination with other technologies like graphical processing units (GPU) with thousands of cores allows us to do much more powerful computations with a much deeper number of layers — hence the term “Deep Learning.”
The following picture from TensorFlow Playground shows an easy-to-use environment that includes various test data sets, configuration options, and visualizations to learn and understand Deep Learning and Neural Networks.
If you want to learn more about the details of Deep Learning and Neural Networks, I recommend the following sources:
While Deep Learning is getting more and more traction, it is not the silver bullet for every scenario.
Deep Learning enables many new possibilities that were not possible in “mass production” a few years ago such as image classification, object recognition, speech translation, or Natural Language Processing (NLP) in much more sophisticated ways than without Deep Learning. A key benefit is automated feature engineering, which costs a lot of time and efforts with most other Machine Learning alternatives.
You can also leverage Deep Learning to make better decisions, increase revenue, or reduce risk for existing (“already solved”) problems instead of using other Machine Learning algorithms. Examples include risk calculation, fraud detection, cross-selling, and predictive maintenance.
However, note that Deep Learning has a few important drawbacks:
Deep Learning is ideal for complex problems. It can also outperform other algorithms in moderate problems. Deep Learning should not be used for simple problems. Other algorithms like logistic regression or decision trees can solve these problems easier and faster.
Neural Networks are mostly adopted using one of various open-source implementations. Various mature Deep Learning frameworks are available for different programming languages.
The following picture shows an overview of open-source Deep Learning frameworks and evaluates several characteristics.
These frameworks have in common that they are built for data scientists, i.e. people with experience in programming, statistics, mathematics, and Machine Learning. Note that writing the source code is not a big task. Typically, only a few lines of codes are needed to build an analytic model. This is completely different from other development tasks like building a web application, where you write hundreds or thousands of lines of code. In Deep Learning (and in Data Science in general), it is most important to understand the concepts behind the code to build a good analytic model.
