< back to All Workshops
artificial intelligence in architecture: exploring GANs, هوش مصنوعی در معماری؛ کاوشی بر شبکه های مولد
Artificial Intelligence | Online Workshop | Farsi | Europe-Mideast-Africa
Description:
Key Words: artificial intelligence,deep learning,neural networks,GAN
Required Skills: familiarity with Python programming language
Required Software: Python,programming language, jupyter notebook
Required Hardware: a laptop or desktop computer highly recommended to have a modern Nvidia GPU on your computer
Maximum number of participating students: 10
This workshop is going to be seven sessions of 3 hours. It consists of three major parts: first, Fundamentals of deep learning, which is about the history of artificial intelligence and the relationship between AI, machine learning, and deep learning. It is also about the mathematics of neural networks. After that, we are going to learn about the basics of neural networks and machine learning. Second, we are going more in-depth in computer vision; we train a neural network from scratch. Then we learn about “transfer learning,” which means how to use a pre-trained neural network. Finally, and most importantly, the last part is about “Generative adversarial networks” (GAN). We will have some experiments with “ neural style transfer” as an example. After that, we will learn about GANs, specifically CycleGAN, and how to implement them.
After this workshop, you know the basics of artificial intelligence, the relationship between machine learning and deep learning. You understand how neural networks work; you can make and implement deep learning models to classify images. You can also make Generative Adversarial Networks to synthesize new images and broaden your horizons.
این کارگاه از سه بخش اصلی تشکیل شده است : نخست، پایه هایی یادگیری عمیق ، که به تشریح و توضیح تاریخچه هوش مصنوعی پرداخته میگردد و پس از آن به تشریح رابطه میان مفاهیمی چون : هوش مصنوعی ، یادگیری ماشین و یادگیری عمیق خواهیم پرداخت. پس از این مباحث به بررسی مباحث ریاضیاتی پشت شبکه های هوش مصنوعی و مفاهیم پایه در شبکه های عصبی و یادگیری ماشین می پردازیم. بخش دوم کارگاه، بررسی عمیق تر بینایی کامپیوتر در دستور کار قرار دارد؛ در این بخش با توسعه و آموزش دادن یک شبکه عصبی از ابتدا به طور عملی با این گونه شبکه ها آشنا میگردیم. پس از این مورد با مفهوم انتقال آموزش که مبحث بسیار جذابی در امر استفاده از شبکه های هوش مصنوعی است آشنا می شویم و چند شبکه حائز اهمیت در این زمینه را بررسی می کنیم. در نهایت سومین بخش و بخش اصلی کارگاه یعنی شبکه های مولد (GAN) - که ترجمه تحت اللفظی آن شبکه مولد خصمانه است – می باشد. در این قسمت با مفاهیمی همچون تغییر سبک عصبی (Neural style transfer) به عنوان پایه ای بر معماری CycleGAN آشنا شده و به طور عملی با این گونه معماری کار خواهیم کرد.
Schedule:
Jun 27 - Jul 3
  • Day 1 / Jun 27

    0:00 - 18:00 (GMT+4:30) Tehran

    |

    15:30 - 09:30 -1 (EST)

    |

    21:30 - 15:30 -1 (CET)

    |

    03:30 - 21:30 (China)

    • A summary of Artificial intelligence, Machine learning, and Deep Learning • A brief mathematical explanation of neural networks building blocks
  • Day 2 / Jun 28

    14:00 - 18:00 (GMT+4:30) Tehran

    |

    05:30 - 09:30 (EST)

    |

    11:30 - 15:30 (CET)

    |

    17:30 - 21:30 (China)

    • Getting started with neural networks • Basics of Machine learning
  • Day 3 / Jun 29

    14:00 - 18:00 (GMT+4:30) Tehran

    |

    05:30 - 09:30 (EST)

    |

    11:30 - 15:30 (CET)

    |

    17:30 - 21:30 (China)

    • Introduction to Convolutional neural networks • Training a convolutional neural network on a small dataset
  • Day 4 / Jun 30

    14:00 - 18:00 (GMT+4:30) Tehran

    |

    05:30 - 09:30 (EST)

    |

    11:30 - 15:30 (CET)

    |

    17:30 - 21:30 (China)

    • Using a pre-trained convolutional neural network • Keras functional API
  • Day 5 / Jul 1

    14:00 - 18:00 (GMT+4:30) Tehran

    |

    05:30 - 09:30 (EST)

    |

    11:30 - 15:30 (CET)

    |

    17:30 - 21:30 (China)

    • neural style transfer
  • Day 6 / Jul 2

    14:00 - 18:00 (GMT+4:30) Tehran

    |

    05:30 - 09:30 (EST)

    |

    11:30 - 15:30 (CET)

    |

    17:30 - 21:30 (China)

    • Introduction to the cycleGAN
  • Day 7 / Jul 3

    14:00 - 18:00 (GMT+4:30) Tehran

    |

    05:30 - 09:30 (EST)

    |

    11:30 - 15:30 (CET)

    |

    17:30 - 21:30 (China)

    • Implementing cycleGAN
Instructors:
  • Mohammed Behjoo University of Tehran,Master's
    As a designer, I am seeking new ways of solving problems. I am interested in computer science, specifically A.I. and deep learning, architecture philosophy, and digital interactive design. I have some experience in digital fabrication. Also, I have worked on a project to solve some of the problems of deaf people. My first teacher was my elder sister when I was three, who teaches me a second language, mathematics, natural sciences, history, etc. So I love to learn new things since I was a little child. I love to teach other people because I can help them believe in themselves regardless of their background or abilities.