Machine Learning with Julia

Contact

Prof. Dr. Claus Möbus

Room: A02 2-226

orcid.org/0000-0003-1640-4168

claus.moebus@uol.de 

-------------------------------------------

Secretary

Manuela Wüstefeld

Room: A02 2-228

Tel: +49 441 / 798-4520

manuela.wuestefeld@uol.de 

-------------------------------------------

Machine Learning with Julia

Machine Learning with Julia/Pluto.jl

These Julia/pluto scripts are inspired by the book Understanding Deep Learning of Simon J.D. Prince, MIT Press, 2024. While Prince published Python scripts in GitHub as to-be-fill-in skeletons for student exercises we develop complete Julia/Pluto scripts to explore the features of Julia and its packages - mainly LUX.jl - to construct neural nets.

  1. Intro
    1. Julia/Pluto-UDL-Notebook_1.1: Background Mathematics
    2. t-Test as Linear Regression with LUX.jl
    3. Multivariate Linear Regression with LUX.jl
  2. Supervised Learning
    1. Julia/Pluto-UDL-Notebook 2.1
    2. Julia/Pluto-Notebook 2.1 with FLUX.jl
    3. Julia/Pluto-Notebook 2.1 with LUX.jl
  3. Shallow Neural Networks
    1. Shallow Neural Networks I
      1. Julia/Pluto-UDL-Notebook 3.1
      2. Julia/Pluto-Notebook 3.1 with FLUX.jl
      3. Julia/Pluto-Notebook 3.1 with LUX.jl
    2. Shallow Neural Networks II
      1. Julia/Pluto-UDL-Notebook 3.2
      2. Julia/Pluto-Notebook 3.2 with FLUX.jl
      3. Julia/Pluto-Notebook 3.2 with LUX.jl
    3. Shallow Network Regions: Julia/Pluto-UDL-Notebook 3.3
    4. Activation functions
      1. Julia/Pluto-UDL-Notebook 3.4
      2. Julia/Pluto-UDL-Notebook 3.4 with FLUX.jl
      3. Julia/Pluto-UDL-Notebook 3.4 with LUX.jl
  4. Deep Neural Networks
    1. Composing Networks
      1. Composing I
      2. Composing II
    2. Clipping Functions
    3. Deep Networks
  5. Loss Functions
    1. Least Squares Loss
    2. Binary Cross-Entropy Loss
    3. Multiclass Cross-Entropy Loss

 

-----------------------------------------------------------------------------------------

This is all draft for personal use; comments, bug reports, or proposals are welcome:

claus.moebus(at)uol.de

-----------------------------------------------------------------------------------------

(Changed: 01 Jul 2024)  | 
Zum Seitananfang scrollen Scroll to the top of the page