Artificial intelligence (AI) is a vast, complicated field. We know, we work with AI every day, and while our work is very rewarding, it\u2019s also extremely challenging. AI is also a diverse field and there are many different subsets, including deep learning and machine learning.<\/p>\r\n\r\n\r\n\r\n
Sometimes these two important and closely related subfields are mixed up. And while they refer to related concepts there are some very important differences. In practice, deep learning and machine learning are used to solve different problems and challenges and each has its own unique strength and limitations.<\/p>\r\n\r\n\r\n\r\n
In this article, we\u2019ll outline what deep learning and machine learning are, why they\u2019re different, and when you should use each. We\u2019ll also examine their intertwined history so you can develop a more complete understanding.<\/p>\r\n\r\n\r\n\r\n
Let\u2019s start by offering a text-book style definition for both:<\/p>\r\n\r\n\r\n\r\n
Machine learning<\/strong> algorithms are created and implemented that allow for self-modification. In other words, no human input is needed. Instead, machine learning programs can analyze structured data and modify themselves based on said data.<\/p>\r\n\r\n\r\n\r\n Deep Learning<\/strong> uses artificial neural networks (ANN) to create multiple layers of algorithms that each offer interpretations of the data feed. Like machine learning, the algorithms can adjust themselves. The ultimate goal of deep learning is to imitate the human brain.<\/p>\r\n\r\n\r\n\r\n Based on the above definitions, you can see that machine learning and deep learning are closely related. In fact, deep learning uses machine learning. As such, some consider it a subset of machine learning.<\/p>\r\n\r\n\r\n\r\n However, deep learning represents such a major breakthrough that this classification may not do it proper justice. One could argue that machine learning is instead a component of deep learning.<\/p>\r\n\r\n\r\n\r\n Don\u2019t worry if you don\u2019t have a full grasp of machine learning and deep learning just yet. Let\u2019s go over an example so you can understand how machine learning and deep learning work and when they are applied. Then we\u2019ll dive into their history.<\/p>\r\n\r\n\r\n\r\n Let\u2019s assume you have a collection of photos of men and women, and you want to sort these photos by sex. With machine learning, you\u2019d use structured data to sort the images. You can create structured data for the images based on specific features, such as long hair, facial structures, the width between eyes, and the like.<\/p>\r\n\r\n\r\n\r\n The machine learning algorithms will then use this structured data to do the sorting. If all goes well, your images will be sorted in no time. However, machine learning requires structured data to work. Often, most data is unstructured<\/a>, and generally developers have to structure the data themselves.<\/p>\r\n\r\n\r\n\r\n Further, if the machine learning algorithm fails to properly sort the images, a human is going to have to step in and adjust the algorithms until they function properly. In practice, this means AI developers may spend a lot of time tweaking machine learning algorithms.<\/p>\r\n\r\n\r\n\r\n Now let\u2019s say you use deep learning instead. With deep learning, you don\u2019t need to provide structured data. Instead, the images can be fed through multiple layers of algorithms, which can identify specific features and then sort them. In this case, queries will be sent through various hierarchies, finding the appropriate identifiers to separate men and women.<\/p>\r\n\r\n\r\n\r\n With deep learning, there is often no need for humans to manually tweak the algorithms. Instead, the deep learning algorithms will adjust themselves until the appropriate outputs are matched. However, deep learning requires a vast amount of high-quality, sortable data.<\/p>\r\n\r\n\r\n\r\n Based on the simplified account above, you might conclude that deep learning is the better technology. However, this isn\u2019t necessarily true. True, deep learning is more complex, and in many, ways more powerful. Still, deep learning requires far more data than machine learning.<\/p>\r\n\r\n\r\n\r\n If the data is not available, the algorithms may not be able to function. In practice, deep learning is only applicable for complex queries and massive data sources. Machine learning, on the other hand, can work with more limited data sources and simpler queries.<\/p>\r\n\r\n\r\n\r\n The development of both machine learning and deep learning represented large leaps in the advance of artificial intelligence. In order to further our understanding of machine and deep learning, let\u2019s put them both in a historical perspective.<\/p>\r\n\r\n\r\n\r\n Machine learning was actually one of the first breakthroughs in the field of artificial intelligence, which was a cutting edge field by the 1950s. Scientists wanted computers to emulate human thinking processes so that they could solve real-world problems.<\/p>\r\n\r\n\r\n\r\n The term \u201cmachine learning\u201d was first coined in 1959 by one of the pioneers of AI, Arthur Samuel. He noted that machine learning was the “field of study that gives computers the ability to learn without being explicitly programmed.”<\/p>\r\n\r\n\r\n\r\n This would greatly reduce the need for human input. Samuel set out to build a computer program that could play checkers and eventually beat skilled humans. Most importantly, Samuel wanted the program to learn as it played.<\/p>\r\n\r\n\r\n\r\n Samuel\u2019s efforts laid the foundation<\/a> for the field of machine learning. Among other things, he outlined a method of rote learning for machines and a scoring function that allowed the machine to calculate the greatest probability of winning with any given checkers board.<\/p>\r\n\r\n\r\n\r\n By the 1960s, machine learning algorithms were becoming quite competent<\/a>, regularly beating humans. Some researchers set their sights on a higher goal: developing a machine learning program that could beat the world\u2019s best chess players.<\/p>\r\n\r\n\r\n\r\n Chess is far more complex than checkers as there are many more outcomes. The first computer to beat a top chess player was IBM\u2019s famous \u201cDeep Blue.\u201d However, Deep Blue didn\u2019t use machine learning, but instead algorithms written by humans<\/a> based on chess best-practices.<\/p>\r\n\r\n\r\n\r\n It\u2019d take a major breakthrough for machine learning-enabled programs to beat world-class competitors in chess and other complex games. As you might have guessed, that breakthrough was deep learning. When it came to more complex games, machine learning simply lacked the \u201cbrain power\u201d needed.<\/p>\r\n\r\n\r\n\r\n Sure, these programs could handle checkers, but chess and other complex games were a whole different story. With chess already conquered by Deep Blue, AI researchers at Google set their sights on an even more audacious goal: beating the world\u2019s best \u201cGo\u201d Player.<\/p>\r\n\r\n\r\n\r\n Go is perhaps the most complicated popular board<\/a> game in the world. This ancient game was invented in ancient China<\/a> and has captivated societies ever since. Go\u2019s rules are simple, you move black and white stones around the board, trying to conquer territory.<\/p>\r\n\r\n\r\n\r\n However, as far as AI is concerned Go, is more complex than checkers or even chess. Why? Consider this: there are more possible variations of stones on the game board than there are atoms in the universe<\/a>. Such a vast amount of data is difficult for AI programs to deal with.<\/p>\r\n\r\n\r\n\r\n For AI researchers, creating an AI program that could teach itself to beat championship level Go players became the perfect benchmark. It didn\u2019t come quickly. Machine learning and deep learning programs were trounced by top Go players for years.<\/p>\r\n\r\n\r\n\r\n In 2017, however, Google\u2019s AlphaGo made a huge breakthrough, first beating South Korean Go Grandmaster Lee Sedol, then taking down Ke Jie<\/a>, who at the time was considered the world\u2019s best human Go player. This was a watershed moment for deep learning, so let\u2019s look at how AlphaGo won.<\/p>\r\n\r\n\r\n\r\nMachine Learning Versus Deep Learning Illustrated<\/strong><\/h2>\r\n\r\n\r\n\r\n
How Deep Learning Approaches the Same Problem<\/strong><\/h2>\r\n\r\n\r\n\r\n
So Which Is Better? It Depends on the Application<\/strong><\/h2>\r\n\r\n\r\n\r\n
The Evolution of Machine Learning and Deep Learning<\/strong><\/h2>\r\n\r\n\r\n\r\n
AI Researchers Target More Complex Games<\/strong><\/h2>\r\n\r\n\r\n\r\n
For Deep Learning, It Was Time to Pass \u201cGo\u201d<\/strong><\/h2>\r\n\r\n\r\n\r\n
How AlphaGo Learned and Then Won<\/strong><\/h2>\r\n\r\n\r\n\r\n