How to understand artificial intelligence - Machine learning?

At SINNETIC, our cognitive services unit develops analytical and artificial intelligence models to solve business challenges. From this standpoint, we observe how artificial intelligence is becoming one of the main tools to modernize industries. But first, to define this concept it is necessary to understand what it means to be an intelligent entity, and then analyze what elements of intelligence we can simulate in software to make them artificial.

An intelligent entity has a central computing system (nervous system in vertebrates) capable of simultaneously actively maintaining at least 9 basic processes (cognitive processes), which are the following:

1. Sensation: It collects information from the environment through sensory channels. In the case of human beings, we have 11 sensory receptors that allow us to be informed of different types of data, sound, color, time, movement, place in space, etc.
   
   
2. Attention: Given that the environment has so much information, we need a system that allows us to select the information that is relevant and functional.
   
   
3. Perception: Then, we need a system that allows us to interpret the information that enters through the sensory channels so that it acquires meaning.
   
   
4. Memory: We must match incoming information with previous experiences. If the incoming information is meaningful, we will need to store it for future references.
   
   
5. Learning: Because of our relationship with the environment, we have to be constantly changing our behavior as we gather experiences.
   
   
6. Reasoning: The incoming information, in addition to the stored information, should allow the expert system to solve problems at different levels of complexity, creating heuristics for that purpose.
   
   
7. Language: An intelligent entity has a system of symbols that allows it to identify and name the environment around it and to communicate with other intelligent entities.
   
   
8. Emotion: The interpretation of environmental information causes the intelligent system to react physiologically to avoid dangers (fear), elude enemies (anger) or maximize adaptive opportunities in its environment (joy).
   
   
9. Motivation: An intelligent system has a set of impulses that guide it to meet adaptation needs, set goals and objectives and interact with other intelligent systems.

These nine processes work together, enabling an intelligent entity to adapt to the changing environment in a versatile way; this facilitates its evolution.

Artificial intelligence consists of programming computer systems that emulate this network of processes through software resources. To achieve this, we must think of the minimum and functional unit of the brain: the neuron, which creates networks with other neurons to transfer information and generate each of the 9 processes described above (Neural networks).

Due to different chemical, structural or functional reasons, an intelligent system can sometimes not be adaptive; thus, in real environments, these processes can be partially or totally disrupted. Some examples may be:

1. Sensation: Different types of pain, tactile sensitivity disorders, paresthetic sensations.
   
   
2. Attention: Decreased attention span, increased attention span 
   
   
3. Perception: delusions, hallucinations 
   
   
4. Memory: Amnesia.
   
   
5. Learning: Dysgraphia, dyslexia, dyscalculia
   
   
6. Reasoning: alterations in problem solving
   
   
7. Language: Aphasia
   
   
8. Emotion: Anxiety
   
   
9. Motivation: Depression

At a computing level, these flaws are equivalent to viruses, programming errors or programming fragments that alter one of these functions. 

To exemplify, let's take a brief look at one of the most famous application cases in artificial intelligence: facial recognition, useful in security, market research, etc.:

1. Sensation: A camera is required to act as a face sensor.
   
2. Attention: A filter is needed, one that bypasses background information and information around the face so that the system can focus solely on the face.
   
3. Perception: Different subsystems are required to recognize various elements of the face, such as expression, symmetry, the distance between specific points, eye size, etc.
   
4. Memory: The incoming image will need to be crosschecked against a database containing historical records of different faces.
   
5. Learning: If the incoming image pairing does not match any face in the database, this face will then be saved as a new one.
   
6. Reasoning: The system can be trained to solve various problems such as: Is it a criminal face? Is it a male or a female? Is it a young person or an adult? What emotion is being expressed?
   
7. Emotion: We can make the system set alarms, in case it is a criminal face for example, or make the system generate a thank you if the emotional expression is favorable.
   
8. Motivation: We can program the system to recognize a certain number of faces and if it does so, expand its memory as a reward or generate task parallelization to spread these tasks among different computing units.

In almost any case where you apply artificial intelligence, you will find a parallel to human psychological processes. Thus, creating intelligent systems would be achieved more efficiently by taking advantage of the enormous amount of research in cognitive psychology, neuropsychology and learning psychology available to date.