Reconciling deep learning with symbolic artificial intelligence: representing objects and relations

Note the similarity to the propositional and relational machine learning we discussed in the last article. The idea was based on the, now commonly exemplified, fact that logical connectives of conjunction and disjunction can be easily encoded by binary threshold units with weights — i.e., the perceptron, an elegant learning algorithm for which was introduced shortly. One of the most successful neural network architectures have been the Convolutional Neural Networks (CNNs) [3]⁴ (tracing back to 1982’s Neocognitron [5]). The distinguishing features introduced in CNNs were the use of shared weights and the idea of pooling. But adding a small amount of white noise to the image (indiscernible to humans) causes the deep net to confidently misidentify it as a gibbon.

This, in turn, enables AI to be trained using multiple techniques, including semantic inferencing and both supervised and unsupervised learning, which will ultimately create AI systems that can reason, learn, and engage in natural language question-and-answer interactions with humans. Already, this technology is finding its way into such complex tasks as fraud analysis, supply chain optimization, and sociological research. Each approach—symbolic, connectionist, and behavior-based—has advantages, but has been criticized by the other approaches. Symbolic AI has been criticized as disembodied, liable to the qualification problem, and poor in handling the perceptual problems where deep learning excels. In turn, connectionist AI has been criticized as poorly suited for deliberative step-by-step problem solving, incorporating knowledge, and handling planning. Finally, Nouvelle AI excels in reactive and real-world robotics domains but has been criticized for difficulties in incorporating learning and knowledge.

Symbolic AI

The weakness of symbolic reasoning is that it does not tolerate ambiguity as seen in the real world. One false assumption can make everything true, effectively rendering the system meaningless. “Neuro-symbolic modeling is one of the most exciting areas in AI right now,” said Brenden Lake, assistant professor of psychology and data science at New York University. His team has been exploring different ways to bridge the gap between the two AI approaches.

However, Cox’s colleagues at IBM, along with researchers at Google’s DeepMind and MIT, came up with a distinctly different solution that shows the power of neurosymbolic AI. The unlikely marriage of two major artificial intelligence approaches has given rise to a new hybrid called neurosymbolic AI. It’s taking baby steps toward reasoning like humans and might one day take the wheel in self-driving cars.

Towards Deep Relational Learning

Find out more on how to host your own Frontiers Research Topic or contribute to one as an author. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. ArXiv is committed to these values and only works with partners that adhere to them. Qualitative simulation, such as Benjamin Kuipers’s QSIM,[89] approximates human reasoning about naive physics, such as what happens when we heat a liquid in a pot on the stove. We expect it to heat and possibly boil over, even though we may not know its temperature, its boiling point, or other details, such as atmospheric pressure.

The justice system, banks, and private companies use algorithms to make decisions that have profound impacts on people’s lives. Unfortunately, those algorithms are sometimes biased — disproportionately impacting people of color as well as individuals in lower income classes when they apply for loans or jobs, or even when courts decide what bail should be set while a person awaits trial. The grandfather of AI, Thomas Hobbes said — Thinking is manipulation of symbols and Reasoning is computation. With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area!

Resources for Deep Learning and Symbolic Reasoning

During training and inference using such an AI system, the neural network accesses the explicit memory using expensive soft read and write operations. They involve every individual memory entry instead of a single discrete entry. The new SPPL probabilistic programming language was presented in June at the ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI), in a paper that Saad co-authored with MIT EECS Professor Martin Rinard and Mansinghka.

Knowable Magazine is from Annual Reviews,

a nonprofit publisher dedicated to synthesizing and

integrating knowledge for the progress of science and the

benefit of society. The words sign and symbol derive from Latin and Greek words, respectively, that mean mark or token, as in “take this rose as a token of my esteem.” Both words mean “to stand for something else” or “to represent something else”. Opposing Chomsky’s views that a human is born with Universal Grammar, a kind of knowledge, John Locke[1632–1704] postulated that mind is a blank slate or tabula rasa. VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. To think that we can simply abandon symbol-manipulation is to suspend disbelief.

Symbolic artificial intelligence

Extensive experiments demonstrate the accuracy and efficiency of our model on learning visual concepts, word representations, and semantic parsing of sentences. Further, our method allows easy generalization to new object attributes, compositions, language concepts, scenes and questions, and even new program domains. It also empowers applications including visual question answering and bidirectional image-text retrieval.

• The hybrid uses deep nets, instead of humans, to generate only those portions of the knowledge base that it needs to answer a given question.
• 1) Hinton, Yann LeCun and Andrew Ng have all suggested that work on unsupervised learning (learning from unlabeled data) will lead to our next breakthroughs.
• It is one form of assumption, and a strong one, while deep neural architectures contain other assumptions, usually about how they should learn, rather than what conclusion they should reach.
• For example, they require very large datasets to work effectively, entailing that they are slow to learn even when such datasets are available.
• Originally, researchers favored the discrete, symbolic approaches towards AI, targeting problems ranging from knowledge representation, reasoning, and planning to automated theorem proving.

Implementations of symbolic reasoning are called rules engines or expert systems or knowledge graphs. Google made a big one, too, which is what provides the information in the top box under your query when you search for something easy like the capital of Germany. These systems are essentially piles of nested if-then statements drawing conclusions about entities (human-readable concepts) and their relations (expressed in well understood semantics like X is-a man or X lives-in Acapulco). Symbolic AI algorithms have played an important role in AI’s history, but they face challenges in learning on their own. After IBM Watson used symbolic reasoning to beat Brad Rutter and Ken Jennings at Jeopardy in 2011, the technology has been eclipsed by neural networks trained by deep learning.

Stacking these on top of each other into layers then became quite popular in the 1980s and ’90s already. However, at that time they were still mostly losing the competition against the more established, and better theoretically substantiated, learning models like SVMs. So, while naysayers may decry the addition of symbolic modules to deep learning as unrepresentative of how our brains work, proponents of neurosymbolic AI see its modularity as a strength when it comes to solving practical problems. “When you have neurosymbolic systems, you have these symbolic choke points,” says Cox. These choke points are places in the flow of information where the AI resorts to symbols that humans can understand, making the AI interpretable and explainable, while providing ways of creating complexity through composition.

Currently, Python, a multi-paradigm programming language, is the most popular programming language, partly due to its extensive package library that supports data science, natural language processing, and deep learning. Python includes a read-eval-print loop, functional elements such as higher-order functions, and symbolic ai object-oriented programming that includes metaclasses. A key component of the system architecture for all expert systems is the knowledge base, which stores facts and rules for problem-solving.[52]

The simplest approach for an expert system knowledge base is simply a collection or network of production rules.