1911 09606 An Introduction to Symbolic Artificial Intelligence Applied to Multimedia

Techniques like BERT, for instance, are based on an approach that works better for facial recognition or image recognition than on language and semantics. Fulton and colleagues are working on a neurosymbolic AI approach to overcome such limitations. The symbolic part of the AI has a small knowledge base about some limited aspects of the world and the actions that would be dangerous given some state of the world. They use this to constrain the actions of the deep net — preventing it, say, from crashing into an object.

In order to understand what’s so special about it, we will take a look at classical methods first. Even though the major advances are currently achieved in Deep Learning, no complex AI system – from personal voice-controlled assistants to self-propelled cars – will manage without one or several of the following technologies. As so often regarding software development, a successful piece of AI software is based on the right interplay of several parts. These soft reads and writes form a bottleneck when implemented in the conventional von Neumann architectures (e.g., CPUs and GPUs), especially for AI models demanding over millions of memory entries. Thanks to the high-dimensional geometry of our resulting vectors, their real-valued components can be approximated by binary, or bipolar components, taking up less storage. More importantly, this opens the door for efficient realization using analog in-memory computing.

Deep Learning: The Good, the Bad, and the Ugly

The rules for the tree and the contents of tables are often implemented by experts of the respective problem domain. In this case we like to speak of an “expert system”, because one tries to map the knowledge of experts in the form of rules. Nevertheless, symbolic AI has proven effective in various fields, including expert systems, natural language processing, and computer vision, showcasing its utility despite the aforementioned constraints. In the paper, we show that a deep symbolic ai examples 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. One promising approach towards this more general AI is in combining neural networks with symbolic AI.

Roughly speaking, the hybrid uses deep nets to replace humans in building the knowledge base and propositions that symbolic AI relies on. It harnesses the power of deep nets to learn about the world from raw data and then uses the symbolic components to reason about it. Symbolic AI, also known as rule-based AI or classical AI, uses a symbolic representation of knowledge, such as logic or ontologies, to perform reasoning tasks. Symbolic AI relies on explicit rules and algorithms to make decisions and solve problems, and humans can easily understand and explain their reasoning. The key innovation underlying AlphaGeometry is its “neuro-symbolic” architecture integrating neural learning components and formal symbolic deduction engines. Samuel’s Checker Program[1952] — Arthur Samuel’s goal was to explore to make a computer learn.

Disadvantages of symbolic AI

“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. Consequently, learning to drive safely requires enormous amounts of training data, and the AI cannot be trained out in the real world. The researchers broke the problem into smaller chunks familiar from symbolic AI. In essence, they had to first look at an image and characterize the 3-D shapes and their properties, and generate a knowledge base.

For instance, while it can solve straightforward mathematical problems, it struggles with more intricate issues like predicting stock market trends. 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. Although operating with 256,000 noisy nanoscale phase-change memristive devices, there was just a 2.7 percent accuracy drop compared to the conventional software realizations in high precision. 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 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. Parsing, tokenizing, spelling correction, part-of-speech tagging, noun and verb phrase chunking are all aspects of natural language processing long handled by symbolic AI, but since improved by deep learning approaches. In symbolic AI, discourse representation theory and first-order logic have been used to represent sentence meanings. Latent semantic analysis (LSA) and explicit semantic analysis also provided vector representations of documents. In the latter case, vector components are interpretable as concepts named by Wikipedia articles. 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.

An LNN consists of a neural network trained to perform symbolic reasoning tasks, such as logical inference, theorem proving, and planning, using a combination of differentiable logic gates and differentiable inference rules. These gates and rules are designed to mimic the operations performed by symbolic reasoning systems and are trained using gradient-based optimization techniques. 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.