The human brain is, as neuroscientist Joseph LeDoux, Ph.D., says in The Emotional Brain (1996), "the most sophisticated machine imaginable, or unimaginable." It’s no wonder, as the brain is composed of more than 100 billion neurons and approximately 1 quadrillion neuron connections altogether.
Perhaps it’s this endless world of possibilities that inspires the field of artificial intelligence (AI), a part of computer science that focuses on machines imitating intelligent human behavior. Since the term was first coined in 1956 by a handful of scientists at the Dartmouth Conferences, AI has made some landmark achievements such as the first self-learning program and the first industrial robot. These advances were made by studying the way the human brain makes decisions, and developing intelligent software and systems based on the outcomes of the studies.
There are many subsets under the umbrella term known as AI. Some subsets, such as machine learning and deep learning, more closely represent the actual complexity of the human brain than others. As you’ll see below, both subsets focus on a machine’s learning capability, but with varying degrees of independence.
Machine learning is one step closer to human cognition in providing computers with the ability to learn without being explicitly programmed. In order to do so, the computer is given an objective and performance measure, and it uses data and algorithms to train itself on how to get closer and closer to the desired outcome until it succeeds.
While this is impressive, the human brain does far more than linear thinking. It takes experience and context into consideration, as well as adapts continuously. For such complex and non-linear deductions, a machine learning technique called “deep learning” is usually applied. While a machine learning model self-learns by being fed more data, a deep learning model goes further by independently learning through its computing “brain.”
The deep learning “brain” is more able to mimic the human brain because of its artificial neural network, which is actually inspired by the biological neural network itself. Traditional machine learning uses shallow nets of two or three layers, but deep learning uses a structure of “deep” neural network of more than three layers. These complex neural networks are more able to categorize intricate links between massive, high-dimensional data sets.
As data gets passed through one layer of nodes to another, each layer trains on a particular set of features based on the previous layer’s output. The deeper into the neural network it goes, the more complex data is processed. This process is commonly referred to as “feature hierarchy” and is best exemplified in tools like image recognition, etc.
On top of this, as time goes on and the system gains more experience, it learns how to increase its probability of a correct classification based on the new data it receives. We see this instilled seamlessly across industries that shape our everyday lives, most of the time without us noticing. E-commerce websites like eBay and Amazon record entire consumer journeys so we get a more engaging experience each time we visit. Medical organizations now use deep learning frameworks with previous research data to detect early signs of disease. Security cameras at airports or secured parking lots everywhere have the ability to detect and track individuals if suspicious activity occurs, all due to their deep learning models.
While all these advances leave us in awe, it’s hard to believe that our human brain is still more advanced and complex than any artificial neural network (by far). This doesn’t mean that AI won’t continue to move towards that direction over time. With every breakthrough, more opportunities will arise that go beyond our wildest imaginations.