Henry Kautz, Francesca Rossi, and Bart Selman have also argued for a synthesis. Their arguments are based on a need to address the two kinds of thinking discussed in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman describes human thinking as having two components, System 1 and System 2. System 1 is the kind used for pattern recognition while System 2 is far better suited for planning, deduction, and deliberative thinking. In this view, deep learning best models the first kind of thinking while symbolic reasoning best models the second kind and both are needed. The CBR approach outlined in his book, Dynamic Memory, focuses first on remembering key problem-solving cases for future use and generalizing them where appropriate.


Knowledge-based systems have an explicit knowledge base, typically of rules, to enhance reusability across domains by separating procedural code and domain knowledge. A separate inference engine processes rules and adds, deletes, or modifies a knowledge store. Apprentice learning systems—learning novel solutions to problems by observing human problem-solving. Domain knowledge explains why novel solutions are correct and how the solution can be generalized.

Neuro-symbolic AI for scene understanding

Sections on Machine Learning and Uncertain Reasoning are covered earlier in the history section. Our chemist was Carl Djerassi, inventor of the chemical behind the birth control pill, and also one of the world’s most respected mass spectrometrists. We began to add in their knowledge, inventing knowledge engineering as we were going along.

Symbolic AI’s adherents say it more closely follows the logic of biological intelligence because it analyzes symbols, not just data, to arrive at more intuitive, knowledge-based conclusions. It’s most commonly used in linguistics models such as natural language processing and natural language understanding , but it is quickly finding its way into ML and other types of AI where it can bring much-needed visibility into algorithmic processes. One such project is the Neuro-Symbolic Concept Learner , a hybrid AI system developed by the MIT-IBM Watson AI Lab. NSCL uses both rule-based programs and neural networks to solve visual question-answering problems. As opposed to pure neural network–based models, the hybrid AI can learn new tasks with less data and is explainable. And unlike symbolic-only models, NSCL doesn’t struggle to analyze the content of images.

Computer Science > Artificial Intelligence

We see Neuro-symbolic AI as a pathway to achieve artificial general intelligence. By augmenting and combining the strengths of statistical AI, like machine learning, with the capabilities of human-like symbolic knowledge and reasoning, we’re aiming to create a revolution in AI, rather than an evolution. Neural networks are almost as old as symbolic AI, but they were largely dismissed because they were inefficient and required compute resources that weren’t available at the time. In the past decade, thanks to the large availability of data and processing power, deep learning has gained popularity and has pushed past symbolic AI systems.

fast and slow

ACT-R has been used successfully to model aspects of human cognition, such as learning and retention. ACT-R is also used in intelligent tutoring systems, called cognitive tutors, to successfully teach geometry, computer programming, and algebra to school children. The symbolic artificial intelligence is entirely based on rules, requiring the straightforward installation of behavioral aspects and human knowledge into computer programs. This entire process was not only inconvenient but it also made the system inaccurate and overpriced . Knowledge graph embedding is a machine learning task of learning a latent, continuous vector space representation of the nodes and edges in a knowledge graph that preserves their semantic meaning. This learned embedding representation of prior knowledge can be applied to and benefit a wide variety of neuro-symbolic AI tasks.

Others also viewed

At the Bosch Resymbolic ai and Technology Center in Pittsburgh, Pennsylvania, we first began exploring and contributing to this topic in 2017. But symbolic AI starts to break when you must deal with the messiness of the world. For instance, consider computer vision, the science of enabling computers to make sense of the content of images and video. Say you have a picture of your cat and want to create a program that can detect images that contain your cat.

What happened to symbolic AI?

Some believe that symbolic AI is dead. But this assumption couldn't be farther from the truth. In fact, rule-based AI systems are still very important in today's applications. Many leading scientists believe that symbolic reasoning will continue to remain a very important component of artificial intelligence.

Prolog provided a built-in store of facts and clauses that could be queried by a read-eval-print loop. The store could act as a knowledge base and the clauses could act as rules or a restricted form of logic. As a subset of first-order logic Prolog was based on Horn clauses with a closed-world assumption — any facts not known were considered false — and a unique name assumption for primitive terms — e.g., the identifier barack_obama was considered to refer to exactly one object. At the height of the AI boom, companies such as Symbolics, LMI, and Texas Instruments were selling LISP machines specifically targeted to accelerate the development of AI applications and research.

Getting AI to reason: using neuro-symbolic AI for knowledge-based question answering

However, the neural aspect of computation dominates the symbolic part in cases where they are clearly separable. We also find that data movement poses a potential bottleneck, as it does in many ML workloads. First of all, every deep neural net trained by supervised learning combines deep learning and symbolic manipulation, at least in a rudimentary sense. Because symbolic reasoning encodes knowledge in symbols and strings of characters. In supervised learning, those strings of characters are called labels, the categories by which we classify input data using a statistical model.

  • Explanations could be provided for an inference by explaining which rules were applied to create it and then continuing through underlying inferences and rules all the way back to root assumptions.
  • While symbolic AI requires every single piece of information, the neural network has the ability to learn on its own if it has been given a large number of data sets.
  • Cybernetic systems like Ashby’s Homeostat, for instance, were based on analogue computation.
  • This is why a human can understand the urgency of an event during an accident or red lights, but a self-driving car won’t have the ability to do the same with only 80 percent capabilities.
  • A truth maintenance system tracked assumptions and justifications for all inferences.
  • The report stated that all of the problems being worked on in AI would be better handled by researchers from other disciplines—such as applied mathematics.

One can provide a “grasping function” that will simply perform inverse kinematics with a magic grasp and focus on the social/theory of mind aspects of a particular learning game. We could go as far as providing a scene graph of existing and visible objects, assuming that identifying and locating objects could potentially be done via deep networks further down the architecture (with potential top-down influence added to the mix). The point is here to focus on the study of the cultural interaction and how the cultural hook works, not on the animal-level intelligence which is, in this developmental approach, not necessarily the most important part to get to human-level intelligence. IBM has demonstrated that natural language processing via the neuro-symbolic approach can achieve quantitatively and qualitatively state-of-the-art results, including handling more complex examples than is possible with today’s AI. Symbols also serve to transfer learning in another sense, not from one human to another, but from one situation to another, over the course of a single individual’s life. That is, a symbol offers a level of abstraction above the concrete and granular details of our sensory experience, an abstraction that allows us to transfer what we’ve learned in one place to a problem we may encounter somewhere else.