Artificial intelligence (AI) is both a tool and a fundamental shift in intelligence used by and for humans. What is this paradigm composed of? Is it evolving well in all aspects of human intelligence? Let us explore.
Artificial intelligence (AI) is getting closer and closer to the heights and depths of human intelligence. That’s what some of us want. That’s what we smell in John McCarthy’s words of AI’s description too. “The science and engineering of making intelligent machines, especially intelligent computer programs.” And all this intelligence comes from building agents that act rationally. That is where we can define the AI technique as a composite of three areas. It is a type of method built on knowledge, which organizes and uses this knowledge and is also aware of its complexity.
- Search in artificial intelligence (AI)
- Knowledge representation in artificial intelligence (AI)
- Abstraction in artificial intelligence (AI)
Let’s break this down one by one.
Search in artificial intelligence (AI)
Artificial intelligence (AI) agents essentially perform some kind of search algorithm in the background to complete their expected tasks. That’s why search is a major building block for any artificial intelligence (AI) solution.
Any artificial intelligence (AI) has a set of states, a start state from where the search begins, and a goal state. By the use of search algorithms, the solution reaches from the start state to the goal state.
This is done through various approaches.
- Blind search
- Uninformed and informed search
- Depth first search
- Breadth first search
- Uniform cost search
- Search heuristics
Knowledge representation in artificial intelligence (AI)
Any artificial intelligence (AI) agent has to work on some input. This work can happen only when there is some knowledge about the input or about its handling. Artificial intelligence (AI), hence, has to be strong in understanding, reasoning, and interpreting knowledge. This is done by the representation of knowledge. It is where the beliefs, intentions, and judgments of an intelligent agent are expressed by reasoning. This is the place for modeling intelligent behavior for an agent.
Here, the representation of information from the real world happens for a computer to understand and leverage this knowledge to solve complex real-life problems. This knowledge can be in the form of the following.
- Declarative knowledge
- Structural knowledge
- Procedural knowledge
- Meta knowledge
- Heuristic knowledge
- Perception component
- Learning component
- Execution component
All this is woven into many ways through logical, semantic, frame, and production rules- as ways of knowledge representation.
Abstraction in artificial intelligence (AI)
When we talk of abstraction, we are looking at an arrangement of the complexity of computer systems. It helps to reduce complexity and achieve a simplified view of various parts and their interplay with each other.
This is very important considering the significant criticism that AI tools face. The ‘black box’ effect is a big problem because a lot of effective and stellar AI models cannot explain how they do what they do. This opacity is a massive barrier to gaining confidence and adoption of artificial intelligence (AI). So several AI techniques span these areas of search, knowledge, and abstraction. Like the following.
- Data Mining – where statistics and artificial intelligence are used for the analysis of large data sets to discover helpful information
- Machine Vision – where the system can use imaging-based automatic inspection and analysis for guidance, decisions, automatic inspection, process control, etc.
- Machine Learning (ML) – where models learn from experience and evolve their precision and delivery over a period
- Natural Language Processing or NLP – where machines can understand and respond to text or voice data
- Robotics – where expert systems can perform tasks like a human.
As we can see, these techniques are evolving and will keep getting better and sharper to bring artificial intelligence (AI) into proximity to the complexity and beauty of human intelligence. We need a lot of work in these areas because we need to address privacy, bias, discrimination, un-explainability, and misapplication that many artificial intelligence (AI) solutions face. We can achieve more trust in AI and its techniques only by getting stronger in all these areas – search, knowledge, and abstraction. That’s where we will remove the most significant gap between a dog and a robot dog – a creature that human intelligence can feel sure of.