Scribd Logo
Upload

Welcome to Scribd!

  • 78 views

    Artificial Intelligence

    Uploaded by

    Pīyush Sīngh
    The document discusses artificial intelligence (AI) and its various subfields including machine learning, deep learning, big data, and data mining. It describes narrow AI which focuses on specific tasks like search engines versus strong AI which aims to mimic general human intelligence. Key techniques discussed are machine learning, neural networks, deep learning, and the programming languages often used in AI like Python, R, C++, Java, Lisp, and SQL.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Artificial Intelligence

    Uploaded by

    Pīyush Sīngh
    78 views8 pages
    The document discusses artificial intelligence (AI) and its various subfields including machine learning, deep learning, big data, and data mining. It describes narrow AI which focuses on specific tasks like search engines versus strong AI which aims to mimic general human intelligence. Key techniques discussed are machine learning, neural networks, deep learning, and the programming languages often used in AI like Python, R, C++, Java, Lisp, and SQL.

    Original Description:

    Ai notes.

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses artificial intelligence (AI) and its various subfields including machine learning, deep learning, big data, and data mining. It describes narrow AI which focuses on specific tasks like search engines versus strong AI which aims to mimic general human intelligence. Key techniques discussed are machine learning, neural networks, deep learning, and the programming languages often used in AI like Python, R, C++, Java, Lisp, and SQL.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    78 views8 pages

    Artificial Intelligence

    Uploaded by

    Pīyush Sīngh
    The document discusses artificial intelligence (AI) and its various subfields including machine learning, deep learning, big data, and data mining. It describes narrow AI which focuses on specific tasks like search engines versus strong AI which aims to mimic general human intelligence. Key techniques discussed are machine learning, neural networks, deep learning, and the programming languages often used in AI like Python, R, C++, Java, Lisp, and SQL.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 8

    Artificial Intelligence (AI)

    Artificial Intelligence is a scientific discipline embracing several Data


    Science fields ranging from narrow AI to strong AI, including machine learning,
    deep learning, big data and data mining.

    Artificial Intelligence is also called Machine Intelligence and Computer


    Intelligence.

    Arthur Samuel 1959:


    "Machine Learning is a subfield of computer science that gives computers the ability to learn without
    being programmed"

    IBM 2022:
    Artificial intelligence leverages computers and machines to mimic the problem-
    solving and decision-making capabilities of the human mind.

    Britannica 2022:
    Artificial intelligence is the ability of a digital computer or computer-controlled
    robot to perform tasks commonly associated with intelligent beings, .... such as
    the ability to reason, discover meaning, generalize, or learn from past
    experience.

    Narrow AI
    Narrow Artificial Intelligence is limited to narrow (specific) areas like most
    of the AI we have around us today:

     Search Engines
     Email spam Filters
     Text to Speech
     Speech Recognition
     Language Translation
     Chatbots
     Netflix's Recommendations
     Apple's Siri
     Microsoft's Cortana
     Amazon's Alexa
     IBM's Watson
     Visual Perception
     Face Recognition

    Narrow AI is also called Weak AI.

    Weak AI:
    Built to simulate human intelligence.

    Strong AI:
    Built to copy human intelligence.

    Strong AI
    Strong Artificial Intelligence is the type of AI that mimics human
    intelligence.

    Strong AI indicates the ability to think, plan, learn, and communicate.

    Strong AI is the theoretical next level of AI: True Intelligence.

    Strong AI moves towards machines with self-awareness, consciousness, and


    objective thoughts.

    Machine Learning (ML)


    Today, Artificial Intelligence is usually referring to Machine
    Learning technologies.
    While traditional computer programming uses rules (algorithms) created by
    humans, machine learning uses technologies where the rules (algorithms) are
    created from the input data (on which the system is trained).

    Classical programming uses programs to create results:

    Data + Computer Program = Result

    Machine Learning uses results to create programs (algorithms):

    Data + Result = Computer Program

    Neural Networks (NN)


    One of the most significant discoveries in history is the power of Neural
    Networks (NN).

    In Neural Networks, many layers of data called Neurons are added together or


    stacked on top of each other to compute new levels of data.

    Commonly used short names:

     DNN Deep Neural Network


     CNN Convolutional Neural Network
     RNN Recurrent Neural Network

    Deep Learning (DL)


    Deep Learning is a subcategory of Machine Learning.

    Deep Learning are algorithms that use Neural Networks to extract higher-level
    data.

    Each successive layer uses the preceding layer as input.

    For instance, optical reading uses low layers to identify edges, and higher layers
    to identify letters.

    Deep Learning has two phases:

    1. Training:
    Input data are used to calculate the parameters of the model.
    2. Inference:
    The "trained" model outputs correct data from any input.

    Big Data
    Big data is data that is impossible for humans to process without the assistance
    of advanced machines.

    Big data does not have any definition in terms of size, but datasets are
    becoming larger and larger as we continously collect more and more data and
    store data at a lower and lower cost.

    Data Mining
    With big data comes complicated data structures.

    A huge part of big data processing is refining data.

    Artificial Intelligence Samples:


     Self Driving Cars
     E-Payment
     Google Maps
     Text Autocorrect
     Automated Translation
     Chatbots
     Social Media
     Face Detection
     Search Algorithms
     Robots
     Automated Investment
     NLP - Natural Language Processing
     Flying Drones
     Dr. Watson
     Apple Siri
     Microsoft Cortana
     Amazon Alexa

    Artificial Music Intelligence


    Can an algorithm compose better music than a human?
    David Cope is a former professor of music at the University of Santa Cruz
    (California).

    For over 30 years, David Cope has been developing Emmy or EMI (Experimental
    Musical Intelligence), an algorithm to compose music in the style of famous
    composers.

    Artificial Health Intelligence


    The Corona Pandemic pushed the need for optimizing Medical Healthcare.

    Machine learning is a new technology that can provide better drug discovery,
    shorter development time, and lower drug costs.

    Machine Learning enables healthcare to use "big data" for making better
    medical or clinical decisions.

    Programming languages involved in Machine Learning and Artificial


    Intelligence are:

     LISP
     R
     Python
     C++
     Java
     JavaScript
     SQL

    LISP
    LISP is the second oldest programming language in the world (1958), one year
    younger than Fortran (1957).

    The term Artificial Intelligence was made up by John McCarthy who


    invented LISP.

    LISP was founded on the theory of Recursive Functions (a function appears in


    its own definition).
    Recursive Functions can be written as self-modifying functions, and this is very
    suitable for Machine Learning programs where "self-learning" is an important
    part of the program.

    The R Language
    R is a programming language for Graphics and Statistical computing.

    R is supported by the R Foundation for Statistical Computing.

    R comes with a wide set of statistical and graphical techniques for:

     Linear Modeling
     Nonlinear Modeling
     Statistical Tests
     Time-series Analysis
     Classification
     Clustering
    Python
    Python is a general-purpose coding language. It can be used for all types of
    programming and software development.

    Python is typically used for server development, like building web apps for web
    servers.

    Python is also typically used in Data Science.

    An advantage for using Python is that it comes with some very suitable
    libraries:

     NumPy (Library for working with Arrays)


     SciPy (Library for Statistical Science)
     Matplotlib (Graph Plotting Library)
     NLTK (Natural Language Toolkit)
     TensorFlow (Machine Learning)

    C++
    C++ holds the title: "The worlds fastest programming language".
    Because of the speed, C++ is a preferred language when programming
    Computer Games.

    It provides faster execution and has less response time which is applied in
    search engines and development of computer games.

    Google uses C++ in Artificial Intelligence and Machine Learning programs for
    SEO (Search Engine Optimization).

    SHARK is a super-fast C++ library with support for supervised learning


    algorithms, linear regression, neural networks, and clustering.

    MLPACK is also a super-fast machine learning library for C++.

    Java
    Java is another general-purpose coding language that can be used for all types
    of software development.

    For Machine Learning, Java is mostly used to create algorithms, and neural
    networks.

    SQL
    SQL (Structured Query Language) is the most popular language for managing
    data.

    Knowledge of SQL databases, tables and queries helps data scientists when
    dealing with data.

    SQL is very convenient for storing, manipulating, and retrieving data in


    databases.

    You might also like