Rules-based systems hard-code knowledge about the world in formal languages, which may lead to problems. System of rules can start of quite simple, but can become rather unwieldy over time as more and more exceptions and rule changes are added. What's more, when the data and scenarios change faster than you can update the rules, you can reach a point when you lose track of what is going on and how many exceptions there are. 

Different from rules-based systems, machine learning has the ability to acquire their own knowledge, by extracting patterns from raw data. Machine learning enabled computers to tackle problems involving knowledge of the real world and make decisions that appear subjective.

While classic machine learning only discovers the mapping from representation to output, representation learning discovers not only the mapping from representation to output but also the representation itself.  Learned representations often result in much better performance than can be obtained with hand-designed representations.

However, when high-level, abstract features such as a speaker's accent can be very difficult to be extracted from raw data, representation learning does not seem to help at first glance.  

Deep learning solves this central problem in representation learning by introducing representations that are expressed in terms of other, simpler representations. Deep learning enables the computer to build complex concepts out of simpler concepts.


Rules-Based Systems vs. Classic Machine Learning vs. Representation Learning vs. Deep Learning

In the dominant machine learning approach, rather than designing explicit step-by-step rules to map inputs to outputs, practitioners define a flexible program whose behavior is governed by a set of adjustable parameters. By presenting this program with a large dataset of examples and labels, a learning algorithm determines the optimal parameter values that maximize the model's performance on the desired task.

Machine Learning Approach

Rules-based systems  are a simple kind of artificial intelligence, which use a series of IF-THEN statements that guide a computer to reach a conclusion or recommendation. The domain experts specify all the steps taken to make a decision and how to handle any special cases and this full knowledge of the experts is hard-coded into the system.


University of Michigan - Ann Arbor

AI is the field of study that incorporates human intelligence onto computer systems in the pursuit of making them capable of performing tasks that require human intelligence.

Artifical Intelligence

Goodfellow, I., Bengio, Y., & Courville, A. (2016). $\mathit{Deep \ Learning.}$ MIT Press. Retrieved from [www.deeplearningbook.org](https://www.deeplearningbook.org) 

Deep Learning

The list of helpful broad references about AI is categorized as follows:
1- AI books
2- AI online courses
3- AI research papers
4- Images related to AI
5- AI videos

Artifical Intelligence references

Rules-Based Systems (A Simple Kind of AI)

- Natural language processing
- Knowledge representation and reasoning
- Planning and scheduling
- Search methodologies
- Control methods
- Philosophical/theoretical foundations of artificial intelligence
- Distributed artificial intelligence
- Computer vision

Artifical Intelligence in ACM Computing Classification

What does the analogy "AI is the new electricity"  refer to?

- Human computer interaction (HCI)
- Interaction design
- Collaborative and social computing
- Ubiquitous and mobile computing
- Data Visualization
- Accessibility

Human-centered computing in ACM Computing Classification

System information consists of contextual details or constraints provided to a Large Language Model (LLM) to guide its response for a specific task. This information helps the LLM understand its expected role, the format of the output, or other operational boundaries.

Learn Before

Related

Learn After