Course Content

  • 1

    1. Python summary for Data Science

    • Environment set up: VS.Code, PIP, VirtualEnv, Jupyter Notebook, Google Colab

  • 2

    2. Introduction to DNN with a high-level view

    • 2.1 Using pre-trained networks and third party libraries:

    • 2.1.1 Colorizing images using Colab

    • 2.1.2 Style transfer using Vs.Code

    • 2.1.3 Generating faces using Colab

    • 2.1.4 Generating and summarizing texts using Colab or Vs.Code

  • 3

    3. Training our first neural network:

    • 3.1 Using Fast.ai and resNet50 with transferlearning

  • 4

    4. Neural Nets from scratch - it is time to get a better understanding of neural networks

    • 4.1 Our goal is to design a neural network to recognize images

    • 4.2 How can we feed an image to a network?

    • 4.3 What is a network after all? - vectors, matrix, linear algebra

    • 4.4 Backpropagation, activation functions

    • 4.5 We will implement our very first neural nets without any library

    • 4.6 Numpy, Tensors

    • 4.7 Recognizing handwritten digits -MNIST

  • 5

    5. Introducing PyTorch and creating our own classifier with CNN

    • 5.1 Convolutional Neural Network using PyTorch

    • 5.2 Creating image dataset from the web

    • 5.3 Using datasets in PyTorch

    • 5.4 Comparing pre-trained and from scratched networks by implementing both

  • 6

    6. Text generation

    • 6.1 One-hot encoding

    • 6.2 Embeddings

    • 6.3 Character level RNN+ LSTM

    • 6.4 Generating text with RNN+LSTM

FAQ

Questions for organizers

  • What is the language of the course?

    It can be either english or hungarian.

  • What is the duration of the course?

    1 week, but It depends of the group. If we are too slow I will skip parts or implementation details, if we are too fast we will start with Reinforcement learning as well.

  • How much does it cost?

    contact us

  • When does the course start?

    The date will be discussed with the customer.

  • Where will be the course?

    At the customer site. Around Budapest, Hungary or Bonn, Germany is preferred. Anything else is up for discussion.

  • Is there a minimum or maximum number of students?

    Contact us to discuss it.

FAQ

Technical questions for the students

  • Do we need to be a Python programmer?

    Python knowledge is necessary for the course. We can offer free online Python course if it is needed, currently in hungarian. Or in english/hungarian onsite, contact for more details.

  • What kind of operating system should we use?

    It does not matter if you are choosing between Linux, Windows or MAC :)

  • Do we need to bring our computers for the course?

    Yes, bring your favorite laptop or desktop computer :)

Oktató

AI expert

Péter Litkei

Az elmúlt pár évben teljesen besszipantott a mesterséges intelligencia, pontosabban a deep neural networks világa. Már most is a legtöbb szolgáltatás használ valamiféle neurális hálót, a jövő egyértelműen ez. A 2012-es ImageNet megváltoztatta a világot és így engem is. A Mesterséges Intelligencián kívül az informatika széles körében szereztem tapasztalatot, a szoftverfejlesztéstől az üzemeltetésen át, a biztonság területe vagy éppen adattárházakkal kapcsolatban. A tanfolyamaim ezért legtöbbször nem csak az adott témáról szólnak, sokszor átnyúlnak más Informatikai területekre is.

This course page is just a placeholder for providing detailed information of the deep neural network onsite training. By subscribing to it means absolutely nothing. To order the onsite training please contact us.