Symbolic AI vs Connectionism Researchers in artificial intelligence by Michelle Zhao Becoming Human: Artificial Intelligence Magazine

For many years, this has meant that teams of scientists, augmented by computers, have been able to extract meaning from data, building an intimate bridge between science and data science. More recently, the sheer size, dimensionality and rate of production of scientific data have become so vast that reliance on automation and intelligent systems has become prevalent. Algorithms can scour data at scales beyond human capacity, finding interesting new phenomena and contributing to the discovery process. Box 5.3 shows examples of AI applications in several research fields. At least one current obstacle to achieving the full potential of AI in science is economic.

We believe that our results are the first step to direct learning representations in the neural networks towards symbol-like entities that can be manipulated by high-dimensional computing. Such an approach facilitates fast and lifelong learning and paves the way for high-level reasoning and manipulation of objects. Learning differentiable functions can be done by learning parameters on all sorts of parameterized differentiable functions. Deep learning framed a particularly fruitful parameterized differentiable function class as deep neural networks, capable to approximate incredibly complex functions over inputs with extremely large dimensionality. Now, if we give up the constraint that the function we try to learn is differentiable, what kind of representation space can we use to describe these functions? Well, the simplest answer to this is to move one step up in terms of generality and consider programs.

OpenAI and Symbolics

It also empowers applications including visual question answering and bidirectional image-text retrieval. Contrasting to Symbolic AI, sub-symbolic systems do not require rules or symbolic representations as inputs. Instead, sub-symbolic programs can learn implicit data representations on their own. Machine learning and deep learning techniques are all examples of sub-symbolic AI models.

Unfortunately, LeCun and Browning ducked both of these arguments, not touching on either, at all. Randy Gallistel and others, myself included, have raised, drawing on a multiple literatures from cognitive science. Although “nature” is sometimes crudely pitted against “nurture,” the two are not in genuine conflict. Nature provides a set of mechanisms that allow us to interact with the environment, a set of tools for extracting knowledge from the world, and a set of tools for exploiting that knowledge.

Category 2: Nested

Differentiable theorem proving [53,54], neural Turing machines [20], and differentiable neural computers [21] are promising research directions that can provide the general framework for such an integration between solving optimization problems and symbolic representations. Third, the two sides often insist on interpreting the same thing very differently. For example, connectionist AI may produce an artificial neural network for an image recognition task and claim that the network does not contain any prior knowledge or perform any reasoning over the knowledge.

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. In addition, several artificial intelligence companies, such as Teknowledge and Inference Corporation, were selling expert system shells, training, and consulting to corporations. 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. So the main challenge, when we think about GOFAI and neural nets, is how to ground symbols, or relate them to other forms of meaning that would allow computers to map the changing raw sensations of the world to symbols and then reason about them. The two biggest flaws of deep learning are its lack of model interpretability (i.e. why did my model make that prediction?) and the large amount of data that deep neural networks require in order to learn.

Human-like generalization in a machine through predicate learning

Connect and share knowledge within a single location that is structured and easy to search. Stack Exchange network consists of 183 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers. Also AutoGPT which recursively plans tasks, and performs them, is gaining traction. This led to a lot of early breakthroughs, but it turned out that these worked very well in labs, in which every variable could be perfectly controlled, but often less well in the messiness of everyday life.

In contrast to the US, in Europe the key AI programming language during that same period was Prolog. 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.

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