Symbolic vs Subsymbolic AI Paradigms for AI Explainability by Orhan G. Yalçın

Such deep nets can struggle to figure out simple abstract relations between objects and reason about them unless they study tens or even hundreds of thousands of examples. One such project is the Neuro-Symbolic Concept Learner (NSCL), 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. The work in AI started by projects like the General Problem Solver and other rule-based reasoning systems like Logic Theorist became the foundation for almost 40 years of research. Symbolic AI (or Classical AI) is the branch of artificial intelligence research that concerns itself with attempting to explicitly represent human knowledge in a declarative form (i.e. facts and rules).

Democratizing the hardware side of large language models

It achieves a form of “symbolic disentanglement”, offering one solution to the important problem of disentangled representations and invariance. Basic computations of the network include predicting high-level objects and their properties from low-level objects and binding/aggregating relevant objects together. These computations operate at a more fundamental level than convolutions, capturing convolution as a special case while being significantly more general than it. All operations are executed in an input-driven fashion, thus sparsity and dynamic computation per sample are naturally supported, complementing recent popular ideas of dynamic networks and may enable new types of hardware accelerations. We experimentally show on CIFAR-10 that it can perform flexible visual processing, rivaling the performance of ConvNet, but without using any convolution. Furthermore, it can generalize to novel rotations of images that it was not trained for.

The problem is that training data or the necessary labels aren’t always available. This directed mapping helps the system to use high-dimensional algebraic operations for richer object manipulations, such as variable binding — an open problem in neural networks. When these “structured” mappings are stored in the AI’s memory (referred to as explicit memory), they help the system learn—and learn not only fast but also all the time.

• Knowledge-based systems have an explicit knowledge base, typically of rules, to enhance reusability across domains by separating procedural code and domain knowledge.
• If one of the first things the ducklings see after birth is two objects that are similar, the ducklings will later follow new pairs of objects that are similar, too.
• Symbolic AI, a branch of artificial intelligence, focuses on the manipulation of symbols to emulate human-like reasoning for tasks such as planning, natural language processing, and knowledge representation.
• For example, debuggers can inspect the knowledge base or processed question and see what the AI is doing.

That broad user base encompasses everyone from C-level executives to subject matter experts and business users such as insurance claims specialists. While it is not theoretically impossible for pure machine learning or statistical AI approaches to deliver explainable AI, they require greater amounts of effort, time, and quantitative skills—which not everyone has, particularly at the scale of deep learning. Symbolic AI is still relevant and beneficial for environments with explicit rules and for tasks that require human-like reasoning, such as planning, natural language processing, and knowledge representation. It is also being explored in combination with other AI techniques to address more challenging reasoning tasks and to create more sophisticated AI systems.

Natural Language Processing

Nowadays it frequently serves as only an assistive technology for Machine Learning and Deep Learning. Deep learning – a Machine Learning sub-category – is currently on everyone’s lips. In order to understand what’s so special about it, we will take a look at classical methods first.

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. Production rules connect symbols in a relationship similar to an If-Then statement. The expert system processes the rules to make deductions and to determine what additional information it needs, i.e. what questions to ask, using human-readable symbols. For example, OPS5, CLIPS and their successors Jess and Drools operate in this fashion. Symbolic artificial intelligence is very convenient for settings where the rules are very clear cut,  and you can easily obtain input and transform it into symbols. In fact, rule-based systems still account for most computer programs today, including those used to create deep learning applications.

Standard neurons are modified so that they precisely model operations in With real-valued logic, variables can take on values in a continuous range between 0 and 1, rather than just binary values of ‘true’ or ‘false.’real-valued logic. LNNs are able to model formal logical reasoning by applying a recursive neural computation of truth values that moves both forward and backward (whereas a standard neural network only moves forward). As a result, LNNs are capable of greater understandability, tolerance to incomplete knowledge, and full logical expressivity. Figure 1 illustrates the difference between typical neurons and logical neurons. One of their projects involves technology that could be used for self-driving cars. “In order to learn not to do bad stuff, it has to do the bad stuff, experience that the stuff was bad, and then figure out, 30 steps before it did the bad thing, how to prevent putting itself in that position,” says MIT-IBM Watson AI Lab team member Nathan Fulton.

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. During the first AI summer, many people thought that machine intelligence could be achieved in just a few years. By the mid-1960s neither useful natural language translation systems nor autonomous tanks had been created, and a dramatic backlash set in. Symbolic AI is a sub-field of artificial intelligence that focuses on the high-level symbolic (human-readable) representation of problems, logic, and search. For instance, if you ask yourself, with the Symbolic AI paradigm in mind, “What is an apple? ”, the answer will be that an apple is “a fruit,” “has red, yellow, or green color,” or “has a roundish shape.” These descriptions are symbolic because we utilize symbols (color, shape, kind) to describe an apple.

Enterprise Tensorflow: Code Examples

Extensions to first-order logic include temporal logic, to handle time; epistemic logic, to reason about agent knowledge; modal logic, to handle possibility and necessity; and probabilistic logics to handle logic and probability together. Semantic networks, conceptual graphs, frames, and logic are all approaches to modeling knowledge such as domain knowledge, problem-solving knowledge, and the semantic meaning of language. DOLCE is an example of an upper ontology that can be used for any domain while WordNet is a lexical resource that can also be viewed as an ontology. YAGO incorporates WordNet as part of its ontology, to align facts extracted from Wikipedia with WordNet synsets.

Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analog to the human concept learning, given the parsed program, the perception module learns visual concepts based on the language description of the object being referred to. Meanwhile, the learned visual concepts facilitate learning new words and parsing new sentences. We use curriculum learning to guide searching over the large compositional space of images and language. Extensive experiments demonstrate the accuracy and efficiency of our model on learning visual concepts, word representations, and semantic parsing of sentences.

The deep nets eventually learned to ask good questions on their own, but were rarely creative. The researchers also used another form of training called reinforcement learning, in which the neural network is rewarded each time it asks a question that actually helps find the ships. Again, the deep nets eventually learned to ask the right questions, which were both informative and creative. Better yet, the hybrid needed only about 10 percent of the training data required by solutions based purely on deep neural networks. When a deep net is being trained to solve a problem, it’s effectively searching through a vast space of potential solutions to find the correct one. Adding a symbolic component reduces the space of solutions to search, which speeds up learning.

The knowledge base would also have a general rule that says that two objects are similar if they are of the same size or color or shape. In addition, the AI needs to know about propositions, which are statements that assert something is true or false, to tell the AI that, in some limited world, there’s a big, red cylinder, a big, blue cube and a small, red sphere. All of this is encoded as a symbolic program in a programming language a computer can understand. One of the main stumbling blocks of symbolic AI, or GOFAI, was the difficulty of revising beliefs once they were encoded in a rules engine.

The Future is Neuro-Symbolic: How AI Reasoning is Evolving

The team’s solution was about 88 percent accurate in answering descriptive questions, about 83 percent for predictive questions and about 74 percent for counterfactual queries, by one measure of accuracy. Such causal and counterfactual reasoning about things that are changing with time is extremely difficult for today’s deep neural networks, which mainly excel at discovering static patterns symbolic ai example in data, Kohli says. A second flaw in symbolic reasoning is that the computer itself doesn’t know what the symbols mean; i.e. they are not necessarily linked to any other representations of the world in a non-symbolic way. Again, this stands in contrast to neural nets, which can link symbols to vectorized representations of the data, which are in turn just translations of raw sensory data.

While this may be unnerving to some, it must be remembered that symbolic AI still only works with numbers, just in a different way. By creating a more human-like thinking machine, organizations will be able to democratize the technology across the workforce so it can be applied to the real-world situations we face every day. Thus contrary to pre-existing cartesian philosophy he maintained that we are born without innate ideas and knowledge is instead determined only by experience derived by a sensed perception. Children can be symbol manipulation and do addition/subtraction, but they don’t really understand what they are doing. Symbolic AI offers clear advantages, including its ability to handle complex logic systems and provide explainable AI decisions. Neural Networks, compared to Symbolic AI, excel in handling ambiguous data, a key area in AI Research and applications involving complex datasets.

While the project still isn’t ready for use outside the lab, Cox envisions a future in which cars with neurosymbolic AI could learn out in the real world, with the symbolic component acting as a bulwark against bad driving. 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. Ducklings exposed to two similar objects at birth will later prefer other similar pairs.

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. And unlike symbolic AI, neural networks have no notion of symbols and hierarchical representation of knowledge. This limitation makes it very hard to apply neural networks to tasks that require logic and reasoning, such as science and high-school math. The advantage of neural networks is that they can deal with messy and unstructured data.

The effectiveness of symbolic AI is also contingent on the quality of human input. The systems depend on accurate and comprehensive knowledge; any deficiencies in this data can lead to subpar AI performance. Despite its early successes, Symbolic AI has limitations, particularly when dealing with ambiguous, uncertain knowledge, or when it requires learning from data. It is often criticized for not being able to handle the messiness of the real world effectively, as it relies on pre-defined knowledge and hand-coded rules. This approach was experimentally verified for a few-shot image classification task involving a dataset of 100 classes of images with just five training examples per class.