Introduction to AI & Machine Learning Part 1.

    Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines that work and reacts like humans.

     

    Some applications of AI include expert systems, speech recognition and machine vision.

    But can we really call this AI , yes but this is not the Ultimate goal of AI , developers looking to create Machines more smarter than Humans , which leads many to warn from this step.

     

    Elon Musk believes that the advancement in technology can create super intelligence that can threaten human existence.

     

    This smart than Human AI ( we call it Artificial Super Intelligence ASI ) could be presented as network of computing power, it can be a human-computer interface(hybrid) or it can be a biologically advanced brain.

     

    But we still far away from that, we did not even reach yet the point where AI machine can be smart as human beings.  (We call it Artificial General Intelligence AGI )

    The Singularity Summit (2012) predicted this may happen around 2040 based on inputs from experts.

     

    Most of the AI systems in place today are Weak Artificial Intelligence (WAI), which were designed to solve a specific problem.

    Such as AlphaGo, who beat human champions in board game.

     

    AI Types:

    • Artificial Super Intelligence (ASI)   , where machines are intelligent & smart more than human beings.
    • Artificial General Intelligence (AGI)  , where machines are intelligent & smart as human beings. This also what we call AI-complete.
    • Weak Artificial Intelligence (WAI), where machines are intelligent & smart less  than human beings in general while it could be smarter in specific task or set of tasks.

     

    We are moving from WAI to AGI but slowly

     

    What is Machine learning , Data Mining &  Data Science?

     

    Machine Learning is a current application of AI based around the idea that we should really just be able to give machines access to data and let them learn for themselves.

    Its where we no longer write rules to generate intelligence rather we will create algorithm that can learn from data.

     

    In conventional programming we write a logic and give it an input, the program produces the output.

    In Machine learning we will give the system a set of inputs and outputs that is associated and the system will generate code for matching these input to output. Once that is done we can use the system to produce output from another set of input.

     

    The key difference between Data Mining & machine learning  is that data mining is about extracting knowledge from data, where machine learning is about learning to work on (or predict) future data from the actual data available now.

    Both Machine learning and Data Mining can contribute to Data Science.

     

    Machine learning classified based on the nature of learning into:

    • Supervised Learning (Input and Output is specified for training),
    • Unsupervised Learning (Only input is given to recognize patterns)
    • Reinforcement learning (Real world feed back is provided to system on the go).

    I will explain more about these types and more in part two of this article

    What is Expert Systems/Knowledge-Based Systems ?

    Expert systems, also called knowledge-based systems, use artificial intelligence (AI) to solve problems.

    The programs that can emulate human expertise in specific domains are called expert systems.

     

    Expert Systems is a computer program containing a knowledge base and a set of algorithms and rules used to infer new facts from data and incoming requests.

     

    Rule-based programming is a common way of developing expert systems.

    The rules are based on if-then logic units and specify a set of actions to be performed for a given

    There  is one way expert systems are used to find patterns, which is called pattern matching.

    A mechanism, called the inference engine, automatically matches facts against patterns and determines which rules are applicable.

     

    1.png

    2.png

     

    What is a neural network?

     

    Artificial neural network (ANN) is a mathematical or computational model based on the neural structure of the brain. Computers perform activities like calculating large

    numbers, keeping large ledgers, and performing complex mathematical functions, but they cannot recognize patterns or learn from experience as the brain can.

    ANNs contain many units that stimulate neurons, each with a small amount of memory.

     

    Artificial neural networks is a computing system that is used for Deep Learning.

    Deep Learning is a type of Machine Learning which includes blocks of Function which can be adjusted on the go to produce better results.

    Most modern deep learning models are based on an artificial neural network

     

    Neural networks itself can be of different types.

    Convolutional neural network is the one which is used for image recognition, where specific connections between nodes in different layers get activated to recognise images.

    There is also fully-connected neural networks with every node in one layer connected to every other node in next layer.

    Connection between nodes are called weights or parameters.

     

    An artificial neural network (ANN) is a mathematical or computational model based on the neural structure of the brain. Computers perform activities like calculating large

    numbers, keeping large ledgers, and performing complex mathematical functions, but they cannot recognize patterns or learn from experience as the brain can.

    ANNs contain many units that stimulate neurons, each with a small amount of memory.

     

    3.png

     

     

    What is Decision Support Systems?

     

    A decision support system (DSS) is a knowledge-based application that analyzes business data and presents it in such a way as to make business decisions easier for users. It is considered more of an informational application than an operational application. Often a DSS is employed by knowledge workers (such as help desk or customer support

    personnel) and by sales services (such as phone operators). This type of application may present information in a graphical manner to link concepts and content and guide the

    script of the operator. Often a DSS is backed by an expert system controlling a database.

     

    4.png

     

    So Simply,

    AI means facts (relationship between objects) & Rules

    Machine Learning means find patterns then predict the future

    Everything is just a set of facts and rules which can help machines to find patterns.

     

    More about how to use Python libraries and the relastionship between Cisco Products and AI/Machine Learining  in the next parts of this article.

     

     

    Yasser Ramzy Auda