Today, artificial intelligence is mostly aboutartificial neural networksanddeep learning.
But this is not how it always was.
Symbolic AI involves the explicit embedding of human knowledge and behavior rules into computer programs.
The practice showed a lot of promise in the early decades of AI research.
The role of symbols in artificial intelligence
Symbols are things we use to represent other things.
Symbols play a vital role in the human thought and reasoning process.
We use symbols all the time to define things (cat, car, airplane, etc.)
and people (teacher, police, salesperson).
They can also describe actions (running) or states (inactive).
It’s free, every week, in your inbox.
Being able to communicate in symbols is one of the main things that make us intelligent.
Therefore, symbols have also played a crucial role in the creation of artificial intelligence.
Therefore, symbolic AI took center stage and became the focus of research projects.
Scientists developed tools to define and manipulate symbols.
Many of the concepts and tools you find in computer science are the results of these efforts.
Symbolic AI programs are based on creating explicit structures and behavior rules.
An example of symbolic AI tools is object-oriented programming.
OOP languages allow you to define classes, specify their properties, and organize them in hierarchies.
you’re able to create instances of these classes (called objects) and manipulate their properties.
Class instances can also perform actions, also known as functions, methods, or procedures.
Using OOP, you’re free to create extensive and complex symbolic AI programs that perform various tasks.
you’re able to easily visualize the logic of rule-based programs, communicate them, and troubleshoot them.
But symbolic AI starts to break when you must deal with the messiness of the world.
This will only work as you provide an exact copy of the original image to your program.
A slightly different picture of your cat will yield a negative answer.
Even if you take a million pictures of your cat, you still wont account for every possible case.
Youll need millions of other pictures and rules for those.
And what if you wanted to create a program that could detect any cat?
How many rules would you oughta create for that?
You cant define rules for the messy data that exists in the real world.
Also, some tasks cant be translated to direct rules, including speech recognition andnatural language processing.
), which will require more human labor.
As some AI scientists point out,symbolic AI systems dont scale.
The advantage of neural networks is that they can deal with messy and unstructured data.
Take the cat detector example.
The neural connection then develops a statistical model for cat images.
When you provide it with a new image, it will return the probability that it contains a cat.
Deep learning and neural networks excel at exactly the tasks that symbolic AI struggles with.
They have created a revolution in computer vision applications such asfacial recognitionand cancer detection.
Deep learning has also driven advances inlanguage-related tasks.
This is the kind of AI that masters complicated games such as Go, StarCraft, and Dota.
Notably, deep learning algorithms are opaque, and figuring out how they workperplexes even their creators.
And its very hard to communicate and troubleshoot their inner-workings.
Neural networks are also very data-hungry.
And unlike symbolic AI, neural networks have no notion of symbols and hierarchical representation of knowledge.
The current state of symbolic AI
Some believe that symbolic AI is dead.
But this assumption couldnt be farther from the truth.
In fact, rule-based AI systems are still very important in todays applications.
Many leading scientists believe thatsymbolic reasoning will continue to remain a very important componentof artificial intelligence.
There are now several efforts to combine neural networks and symbolic AI.
NSCL uses both rule-based programs and neural networks to solve visual question-answering problems.
And unlike symbolic-only models, NSCL doesnt struggle to analyze the content of images.
Maybe in the future, well invent AI technologies that can both reason and learn.
you could read the original articlehere.
