Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 36 views

    02 Dasar JST

    Uploaded by

    Agus Sugiharto
    - The document discusses the basics of artificial neural networks, including their biological inspiration from the human brain. It describes key aspects of the brain like the large number of neurons and synapses, distributed and parallel processing, and tolerance to noise. - Artificial neural networks are also discussed in comparison to the brain and traditional computer architectures. Some key differences highlighted are that ANNs use many slow processors in parallel while computers use a single fast processor, and that ANNs use non-linear and distributed processing while computers use linear and centralized processing. - The document concludes that artificial neural networks are inspired by the structure of the human brain, and introduces the perceptron as the simplest form of artificial neural network.

    Copyright:

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

    02 Dasar JST

    Uploaded by

    Agus Sugiharto
    36 views16 pages
    - The document discusses the basics of artificial neural networks, including their biological inspiration from the human brain. It describes key aspects of the brain like the large number of neurons and synapses, distributed and parallel processing, and tolerance to noise. - Artificial neural networks are also discussed in comparison to the brain and traditional computer architectures. Some key differences highlighted are that ANNs use many slow processors in parallel while computers use a single fast processor, and that ANNs use non-linear and distributed processing while computers use linear and centralized processing. - The document concludes that artificial neural networks are inspired by the structure of the human brain, and introduces the perceptron as the simplest form of artificial neural network.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    - The document discusses the basics of artificial neural networks, including their biological inspiration from the human brain. It describes key aspects of the brain like the large number of neurons and synapses, distributed and parallel processing, and tolerance to noise. - Artificial neural networks are also discussed in comparison to the brain and traditional computer architectures. Some key differences highlighted are that ANNs use many slow processors in parallel while computers use a single fast processor, and that ANNs use non-linear and distributed processing while computers use linear and centralized processing. - The document concludes that artificial neural networks are inspired by the structure of the human brain, and introduces the perceptron as the simplest form of artificial neural network.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    36 views16 pages

    02 Dasar JST

    Uploaded by

    Agus Sugiharto
    - The document discusses the basics of artificial neural networks, including their biological inspiration from the human brain. It describes key aspects of the brain like the large number of neurons and synapses, distributed and parallel processing, and tolerance to noise. - Artificial neural networks are also discussed in comparison to the brain and traditional computer architectures. Some key differences highlighted are that ANNs use many slow processors in parallel while computers use a single fast processor, and that ANNs use non-linear and distributed processing while computers use linear and centralized processing. - The document concludes that artificial neural networks are inspired by the structure of the human brain, and introduces the perceptron as the simplest form of artificial neural network.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 16

    Kredensial Mikro

    Mahasiswa Indonesia

    Dasar-dasar Jaringan
    Syaraf Tiruan
    Khairul Anam (khairul@unej.ac.id)
    Universitas Jember, 2021

    KURSUS KMMI: MACHINE LEARNING & DEEP LEARNING FOR AGROINDUSTRY


    Artificial Neural Networks
    • History
    • 1943-McCulloch & Pitts are generally recognised as the designers of
    the first neural network
    • 1949-First learning rule
    • 1969-Minsky & Papert - perceptron limitation - Death of ANN
    • 1980’s - Re-emergence of ANN - multi-layer networks
    • 2010 - .. Deep Learning
    Biological Inspiration
    • The brain has been extensively studied by scientists.
    • Vast complexity prevents all but rudimentary understanding.
    • Even the behaviour of an individual neuron is extremely
    complex
    The features of brain
    • Ten billion (1010) neurons
    • Neuron switching time >10-3secs
    • Face Recognition ~0.1secs
    • On average, each neuron has several thousand connections
    • Hundreds of operations per second
    • High degree of parallel computation
    • Distributed representations
    • Die off frequently (never replaced)
    • Compensated for problems by massive parallelism
    Brain and Machine

    • The Brain
    – Pattern Recognition
    – Association
    – Complexity
    – Noise Tolerance

    • The Machine
    – Calculation
    – Precision
    – Logic
    Architecture

    • The Von Neumann architecture uses


    a single processing unit;
    – Tens of millions of operations per second
    – Absolute arithmetic precision

    • The brain uses many slow


    unreliable processors acting in
    parallel
    Brain vs Computer

    1. 10 billion neurons 1. Faster than neuron (10-9 sec)


    2. 60 trillion synapses cf. neuron: 10-3 sec
    3. Distributed processing 3. Central processing
    4. Nonlinear processing 4. Arithmetic operation (linearity)
    5. Parallel processing 5. Sequential processing
    Jaringan Syaraf Biologis
    Artificial Neural Networks

    Dendrite Axon
    Cell Body
    Jaringan Syaraf Tiruan
    • Bobot (weights)
    • Threshold
    • Fungsi aktivasi
    Fungsi aktivasi

    Linear Hard-limiter biner Hard-limieter bipolar

    JST dengan hard-limtter è


    McCulloch-Pitts model
    Fungsi aktivasi
    •a
    Contoh:
    Perceptron: JST Sederhana

    Perceptron adalah linear classifier. Bagus jika datanya terpisah secara linear.
    Jika datanya tercampur bagaimana???
    Kesimpulan
    • Jaringan syaraf tiruan (JST) terinspirasi dari struktur syaraf
    manusia
    • Perceptron adalah JST paling sederhana
    Materi Selanjutnya

    Perceptron dan Turunannya

    You might also like