Machine Learning vs. Deep Learning – Understanding the Difference

Machine learning vs. deep learning

As product managers, we’re going to need to build a lot of trust with our technical counterparts so that, together, we can build an amazing product that works as well as it can technically. If you’re reading this course, you’ve likely come across the phrases ML and DL. We will use the following sections titled ML and DL to go over some of the basics, but keep in mind that we will be elaborating on these concepts in later lessons.

Machine learning

In its basic form, ML is made up of two essential components:

• The models used

• The training data it’s learning from

These data are historical data points that effectively teach machines a baseline foundation from which to learn, and every time we retrain the models, the models are theoretically improving. How the models are chosen, built, tuned, and maintained for optimized performance is the work of data scientists and ML engineers. Using this knowledge of performance toward the optimization of the product experience itself is the work of product managers. If we’re working in the field of AI product management, we’re working incredibly closely with our data science and ML teams.

These are the four major areas of ML, and each area is going to have its particular models and algorithms that are used in each specialization. The learning type has to do with whether or not we’re labeling the data and the method we’re using to reward the models we’ve used for good performance. These learning types are relevant whether our product is using a DL model or not, so they’re inclusive of all ML models.

Deep learning

DL is a subset of ML, but the terms are often used colloquially as almost separate expressions. The reason for this is DL is based on neural network algorithms, and ML can be thought of as… the rest of the algorithms. In ML, we take data, use it to train our models, and use that trained model to predict new future data points. Every time we use the model, we see how off it was from the correct answer by getting some understanding of the rate of error so we can iterate back and forth until we have a model that works well enough. Every time, we are creating a model based on data that has certain patterns or features.

This process is the same in DL, but one of the key differences of DL is that patterns or features in our data are largely picked up by the DL algorithm through what’s referred to as feature learning or feature engineering through a hierarchical layered system. We’ll go into the various algorithms because there are a few nuances between each, but as we continue developing our understanding of the types of ML out there, we’ll also start to group the various models that make up these major areas of AI (ML and DL). For marketing purposes, we’ll, for the most part, see terms such as ML, DL/neural networks, or just the general umbrella term of AI referenced where DL algorithms are used.

Opaque-box models

It’s important to know the difference between what these terms mean in practice and, at the model level, how they’re communicated by non-technical stakeholders. As product managers, we are toeing the line between the two worlds: what engineering is building and what marketing is communicating. Anytime we’ve heard the term opaque-box model, it’s referring to a neural network model, which is DL. The reason for this is DL engineers often can’t determine how their models are arriving at certain conclusions, creating an opaque view of what the model is doing. This opacity is double-sided, both for the engineers and technologists themselves, as well as for the customers and users downstream who are experiencing the effects of these models without knowing how they make certain determinations. The DL neural networks are mimicking the structure of the way humans are able to think using a variety of layers of neural networks.

Challenges for AI product managers

For product managers, DL poses a concern for understandability because there’s very little we can understand about how and why a model is arriving at conclusions, and depending on the context of our product, the importance of understandability could vary. Another inherent challenge is these models essentially learn autonomously because they aren’t waiting for their engineer to choose the features that are most relevant in the data for them; the neural networks themselves do the feature selection. It learns with very little input from an engineer. Think of the models as the what and the following section of learning types as the how.