Git Product home page Git Product logo

nikronic / coursera-machine-learning Goto Github PK

View Code? Open in Web Editor NEW
13.0 2.0 4.0 9.85 MB

In this repository I implemented all assignments in python for the purpose of learning python

License: MIT License

Jupyter Notebook 100.00%
machine-learning deep-learning artificial-neural-networks linear-regression logistic-regression regularization multiclass-classification bias-variance polynomial-regression coursera-machine-learning

coursera-machine-learning's Introduction


Hi there ๐Ÿ‘‹

I am Nikan Doosti
'Nikan' means genuine and good and it's Persian originated name, and 'Doosti' literally means friendship!

About

I am a master's graduate of Computer Engineering (Artificial Intelligence) from Iran University of Science and Technology (IUST) one of the most prestigious universities in Iran.
In my work, I utilize Artificial Intelligence to provide data-driven decision making for different services. Previously, I did a research internship at Max Planck Institute for Informatics at AIDAM group in Germany ๐Ÿ‡ฉ๐Ÿ‡ช, working on applications of machine learning in fabrication. Prior to that, I was mainly focused on classic computer vision, specifically digital image processing.

  • ๐Ÿง I'm interested in devising self-supervised deep learning models for efficient and accurate modeling, and I always love to work on interdisciplinary topics such as intersection of AI and Science/Engineering.
  • ๐ŸŒฑ I'm currently (re)learning C++ and started learning MLOps.
  • ๐Ÿ‘ฏ I'm looking to collaborate on PyTorch framework. Meet me on official PyTorch forum: PyTorch Discuss
  • ๐Ÿ’“ I'd love to play games, particularly video games. I mostly play Dota 2 and CnC Generals ZH. I am noob in execution (slow body, eyes, FPS, and refresh rate :D), but I plan well!
  • ๐Ÿ’ฌ Ask me about anything, but I don't know how much I don't know. However, I know a bit about AI and Computer Graphics/Vision.
  • ๐Ÿ“ซ How to reach me: My email nikan [dot] doosti [at] outlook [dot] com (more details on the bottom of home page of my website)
  • โญ Giving stars is a small gesture, but it means a lot! So give stars to cool projects.

I follow Github timeline almost everyday (Works as a social media for me :D).


coursera-machine-learning's People

Contributors

nikronic avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

coursera-machine-learning's Issues

Unregularized or Regularized version of cost function

In the ex3.pdf, instructor says we should write unregularized cost function in the file lrCostFunction but in this file,all comments are about regularized version of cost function. So we implement and compare our result to understand which is correct.
(regularized should be correct because of too many parameters - prevent overfitting)

Optimizer do not work!

Week 5 - Backpropagation
scipy.fmin_cg is not working because of precision error. I think the problem is we should use one dimensional x instead of passing x as a matrix.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.