Beyond the symbolic vs non-symbolic AI debate by JC Baillie

As we got deeper into researching and innovating the sub-symbolic computing area, we were simultaneously digging another hole for ourselves. Yes, sub-symbolic systems gave us ultra-powerful models that dominated and revolutionized every discipline. But as our models continued to grow in complexity, their transparency continued to diminish severely.

So the same way we actually built these computers which take something that’s crystal perfect and it can produce something that’s still crystal perfect. And while all at the same time this seems to be missing in the language model, this sort of aspect is not quite there. We write down symbols and into the symbols we can even encode rules. And the rules can operate on the symbols and it’s like a perfect system. It was super successful in understanding the world because we used it to create mathematics, which was used for accounting, physics, and engineering.

The Various Types of Artificial Intelligence Technologies

These model structures can then be analyzed instead of syntactically formed graphs, and for example used to define similarity measures [13]. The Life Sciences are a hub domain for big data generation and complex knowledge representation. Life Sciences have long been one of the key drivers behind progress in AI, and the vastly increasing volume and complexity of data in biology is one of the drivers in Data Science as well. Life Sciences are also a prime application area for novel machine learning methods [2,51]. Similarly, Semantic Web technologies such as knowledge graphs and ontologies are widely applied to represent, interpret and integrate data [12,32,61].

Implicit knowledge refers to information gained unintentionally and usually without being aware. Therefore, implicit knowledge tends to be more ambiguous to explain or formalize. Examples of implicit human knowledge include learning to ride a bike or to swim.

Neuro-Symbolic AI: A Reunion of Symbol and Neuron

I recall the excitement in the AI research community about the potential for understanding and building intelligence in the empiricist school without requiring knowledge and inferencing. Then, as now, there was joy in the AI research community, and perhaps also a little surprise, that the connectionist techniques had been successful at an increasing number of tasks. Then, as now, we heard claims from connectionists that symbolic AI has failed, and that connectionist AI can do everything symbolic AI can do, or soon will, all without requiring knowledge and inferencing. Then, as now, we read about the skepticism of symbolicists about some of the connectionist claims, and doubts that the connectionist models, even if successful at some narrow tasks, are actually intelligent in any deep sense. If you wanted to learn more about this, there are companies and people which publish things in this domain. For example, on Twitter, you can follow Gary Marcus, you can follow Francois Chollet, and other authors of the papers.

Symbols can be organized into hierarchies (a car is made of doors, windows, tires, seats, etc.). They can also be used to describe other symbols (a cat with fluffy ears, a red carpet, etc.). Human intervention usually happens at several steps throughout the journey, depending on the complexity of the problem. At the start, however, the set of rewards is defined — winning a game, taking a piece, etc.

Cyc has attempted to capture useful common-sense knowledge and has “micro-theories” to handle particular kinds of domain-specific reasoning. Programs were themselves data structures that other programs could operate on, allowing the easy definition of higher-level languages. This process is experimental and the keywords may be updated as the learning algorithm improves.

In contrast, a multi-agent system consists of multiple agents that communicate amongst themselves with some inter-agent communication language such as Knowledge Query and Manipulation Language (KQML). Advantages of multi-agent systems include the ability to divide work among the agents and to increase fault tolerance when agents are lost. Research problems include how agents reach consensus, distributed problem solving, multi-agent learning, multi-agent planning, and distributed constraint optimization. Forward chaining inference engines are the most common, and are seen in CLIPS and OPS5. Backward chaining occurs in Prolog, where a more limited logical representation is used, Horn Clauses.

It still involves letting the machine learn from data, but it marks a milestone in AI’s evolution. When deep learning reemerged in 2012, it was with a kind of take-no-prisoners attitude that has characterized most of the last decade. By 2015, his hostility toward all things symbols had fully crystallized. He gave a talk at an AI workshop at Stanford comparing symbols to aether, one of science’s greatest mistakes.

Read more about https://www.metadialog.com/ here.