Introduction to Artificial Intelligence

Definition
Artificial Intelligence (AI) is the ability of a computer program or computer controlled robot to perform tasks associated with human beings and other animals. These tasks can be; the ability to reason, discover meaning, generalize, or learn from past experience. Informally, It can also be defined as a machine that can mimics the “cognitive” associated with human minds. Here, “cognitive” is a mental activity associated with thinking, learning and memory.

Characteristics of AI
The purpose of AI is to create technology that allows computers and machines to function in an intelligent manner. In the process of building such technology or machine, creator must make sure that the particular characteristics or capabilities must appear in his computer or machine. These major characteristics are as follows: -
1)     Reasoning or Problem solving (like common sense knowledge)
2)     Knowledge representations (knowledge about the world like objects, properties, categories, situation, events, time, states, causes, effects, knowledge about knowledge, etc.)
3)     Planning (ability to set goals and achieve them)
4)     Learning (ability to study computer algorithms and improve automatically with experience)
5)     Natural language processing (ability to read and understand human language)
6)     Perception (ability to use input from sensors like camera and microphone to understand the aspects of the world)
7)     Motion and manipulation (ability to build a map from its environment and moving from one point in space to another and executing this movement)
8)     Social intelligence (ability to predict the actions of others by understanding their motives and emotional states)
9)     Creativity (philosophical and psychological perspective)
10)  General intelligence

Approaches
In order to build AI, you must be looking for some kind approach system, but, there is no standard or unified approach that can guide you to build AI. Stuart Shapiro has three approaches for building AI those are Computational Philosophy (developing adaptive and free-flowing computer mind), Computational Psychology (computer program that mimics human behavior) and Computer Science (helping computer perform that only people could previously accomplish) when implemented all three together; behavior, mind and actions, it makeup artificial Intelligence. Other approaches were also introduced that were inspired from the work of Stuart Shapiro, those are Symbolic (also known as top-down), Connectionist (also known as bottom-up), Strong AI, Applied AI and Cognitive Simulation.

Evaluating AI
In 1950, Alan Turing proposed a general procedure to test the intelligence of an agent now known as the Turing test. This procedure allows almost all the major problems of artificial intelligence to be tested. However, it is a very difficult challenge and at present all agents fail.
Artificial intelligence can also be evaluated on specific problems such as small problems in chemistry, hand-writing recognition and game-playing. Such tests have been termed subject matter expert Turing tests. Smaller problems provide more achievable goals and there are an ever-increasing number of positive results.
For example, performance at draughts (i.e. checkers) is optimal, performance at chess is high-human and nearing super-human and performance at many everyday tasks (such as recognizing a face or crossing a room without bumping into something) is sub-human.
A quite different approach measures machine intelligence through tests which are developed from mathematical definitions of intelligence. Examples of these kinds of tests start in the late nineties devising intelligence tests using notions from Kolmogorov complexity and data compression. Two major advantages of mathematical definitions are their applicability to nonhuman intelligences and their absence of a requirement for human testers.
A derivative of the Turing test is the Completely Automated Public Turing test to tell Computers and Humans Apart (like CAPTCHA). As the name implies, this helps to determine that a user is an actual person and not a computer posing as a human. In contrast to the standard Turing test, CAPTCHA is administered by a machine and targeted to a human as opposed to being administered by a human and targeted to a machine. A computer asks a user to complete a simple test then generates a grade for that test. Computers are unable to solve the problem, so correct solutions are deemed to be the result of a person taking the test. A common type of CAPTCHA is the test that requires the typing of distorted letters, numbers or symbols that appear in an image undecipherable by a computer.

Applications
AI is relevant to any intellectual task. High-profile examples of AI include autonomous vehicles (such as drones and self-driving cars), medical diagnosis, creating art (such as poetry), proving mathematical theorems, playing games (such as Chess or Go), search engines (such as Google or Bing search), online assistants (such as Siri or Cortana), image recognition in photographs, spam filtering, prediction of judicial decisions and targeting online advertisements.
With social media sites overtaking TV as a source for news for young people and news organisations increasingly reliant on social media platforms for generating distribution, major publishers now use artificial intelligence (AI) technology to post stories more effectively and generate higher volumes of traffic.

Platforms for building AI
A wide variety of platforms has allowed different aspects of AI to develop, ranging from expert systems such as Cyc to deep-learning frameworks to robot platforms such as the Roomba with open interface. Recent advances in deep artificial neural networks and distributed computing have led to a proliferation of software libraries, including Deeplearning4j, TensorFlow, Theano, Torch and Collective AI.


References:-
1.     https://www.britannica.com/technology/artificial-intelligence
2.     https://en.wikipedia.org/wiki/Artificial_intelligence 


Comments

Post a Comment

Popular posts from this blog

Hashicorp Configuration Language - HCL

Installing Terraform What is Terraform and Why do we need it? Terraform Commands Here, we will cover the basics of the Terraform configuration language, as well as explore providers and resources. Continuing what we started in Terraform Commands, we will modify main.tf so we can deploy a Ghost container to Docker. The syntax of Terraform configurations is called HashiCorp Configuration Language (HCL). It is meant to strike a balance between being human-readable and editable, and being machine-friendly. For machine-friendliness, Terraform can also read JSON configurations. For general Terraform configurations, however, we recommend using the HCL Terraform syntax. Terraform code files The Terraform language uses configuration files that are named with the .tf file extension. There is also a JSON-based variant of the language that is named with the .tf.json file extension. Terraform Syntax Here is an example of Terraform's HCL syntax: resource "aws_instance" "example...
Read more

Terraform - Input Variables

Installing Terraform What is Terraform and Why do we need it? Terraform Commands Hashicorp Configuration Language - HCL Tainting and Untainting Resources Terraform Console and Output Input variables serve as parameters for a Terraform file. A variable block configures a single input variable for a Terraform module. Each block declares a single variable. Syntax: variable [NAME] {   [OPTION] = "[VALUE]" } Arguments Within the block body (between { }) is configuration for the variable, which accepts the following arguments: type (Optional): If set, this defines the type of the variable. Valid values are string, list, and map. default (Optional): This sets a default value for the variable. If no default is provided, Terraform will raise an error if a value is not provided by the caller. description (Optional): A human-friendly description for the variable. Using variables during an apply: terraform apply -var 'foo=bar' Set up the environment: cd terraform/basics Edit main...
Read more

Terraform - Tainting and Updating Resources

Installing Terraform What is Terraform and Why do we need it? Terraform Commands Hashicorp Configuration Language - HCL We are going to take a look at how to force a redeploy of resources using tainting. This is an extremely useful skill for when parts of a deployment need to be modified. Tainting and Untainting Resources Terraform commands: taint: Manually mark a resource for recreation  untaint: Manually unmark a resource as tainted Tainting a resource: terraform taint [NAME] Untainting a resource: terraform untaint [NAME] Set up the environment: cd terraform/basics Redeploy the Ghost image: terraform apply Taint the Ghost blog resource: terraform taint docker_container.container_id See what will be changed: terraform plan Remove the taint on the Ghost blog resource: terraform untaint docker_container.container_id Verity that the Ghost blog resource is untainted: terraform plan Updating Resources Let's edit main.tf and change the image to ghost:alpine. Open main.tf: vi main.tf ma...
Read more