Another benefit of combining the techniques lies in making the AI model easier to understand. Humans reason about the world in symbols, whereas neural networks encode their models using pattern activations. Another compelling use case for composite AI is the predictive accuracy of Graph Neural Networks . These machine learning models excel in graph settings that fully depict or visualize all of the dimensions of their statistical analytics on multi-dimensionality data—like considerations across networks for fraud analysis, for example.
One very interesting aspect of the VR approach is that it allows us to shortcut these issues if needed . 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. We’ve relied on the brain’s high-dimensional circuits and the unique mathematical properties of high-dimensional spaces. Specifically, we wanted to combine the learning representations that neural networks create with the compositionality of symbol-like entities, represented by high-dimensional and distributed vectors. The idea is to guide a neural network to represent unrelated objects with dissimilar high-dimensional vectors. 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. But the benefits of deep learning and neural networks are not without tradeoffs.
It learns to understand the world by forming internal symbolic representations of its “world”. In the paper, we show that a deep convolutional neural network used for image classification can learn from its own mistakes to operate with the high-dimensional computing paradigm, using vector-symbolic architectures. It does so by gradually learning to assign dissimilar, such as quasi-orthogonal, vectors to different image classes, mapping them far away from each other in the high-dimensional space. To better simulate how the human brain makes decisions, we’ve combined the strengths of Symbolic AI and neural networks. The technology actually dates back to the 1950s, says expert.ai’s Luca Scagliarini, but was considered old-fashioned by the 1990s when demand for procedural knowledge of sensory and motor processes was all the rage.
— Global Vacancies (@VacanciesGlobal) July 3, 2022
Hatchlings shown two red spheres at birth will later show a preference for two spheres of the same color, even if they are blue, over two spheres that are each a different color. Somehow, the ducklings pick up and imprint on the idea of similarity, in this case the color of the objects. Ontologies are data sharing tools that provide for interoperability through a computerized lexicon with a taxonomy and a set of terms and relations with logically structured definitions. Being able to communicate in symbols is one of the main things that make us intelligent.
This is a nice coupling of statistical evaluation and formal structure evolution, which comes with many computational advantages once the final grammar has been stabilized. 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. The ideal, obviously, is to choose assumptions that allow a system to learn flexibly and produce accurate decisions about their inputs. In the CLEVR challenge, artificial intelligences were faced with a world containing geometric objects of various sizes, shapes, colors and materials. https://metadialog.com/ The AIs were then given English-language questions about the objects in their world. Also, some tasks can’t be translated to direct rules, including speech recognition and natural language processing. Symbolic artificial intelligence showed early progress at the dawn of AI and computing. You can easily visualize the logic of rule-based programs, communicate them, and troubleshoot them. Until now, while we talked a lot about symbols and concepts, there was no mention of language. Tenenbaum explained in his talk that language is deeply grounded in the unspoken commonsense knowledge that we acquire before we learn to speak.