Introduction to Machine Learning and Deep Learning

What is in this section?

In the age of AI implementation, the current period of AI we find ourselves in, we must understand the pros and cons of both ML and DL in order to best navigate when to use either technology. Some other terms we might have come across with respect to AI/ML tools are applied AI or deep tech. As we’ve mentioned a few times over the course, the underlying tech that will, for the most part, power AI products will be ML or DL. That’s because expert or rule-based systems are slowly being powered by ML or not evolving at all. So, let’s dive a bit further into these technologies and understand how they differ.

In this section, we will explore the relationship between ML and DL and the way in which they bring their own sets of expectations, explanations, and elucidations to builders and users alike. Whether we work with products that incorporate ML models that have been around since the 50s or use cutting-edge models that have sprung into use recently, we’ll want to understand the implications either way. Incorporating ML or DL into our product will have different repercussions. Most of the time, when we see an AI label on a product, it’s built using ML or DL, so we want to make sure we come out of this section with a firm understanding of how these areas differ and what this difference will tangibly mean for our future products.

We wanted to expand on the history of ML and DL artificial neural networks (ANNs) to give us a sense of how long these models have been around. In this section, we will cover the following topics to get more familiar with the nuances related to ML and DL:

• “The Old: Exploring ML”

• “The New: Exploring DL”

• “A Brief History of DL”

• “Types of Neural Networks”

• “Emerging Technologies”

• “Explainability and Accuracy”