Giter VIP home page Giter VIP logo

100daysofmlcode's Introduction

100DaysOfMLCode

Day 0: 14th July 2018

I've just created this repository and I'm learning how to properly use GitHub, watching the video https://www.youtube.com/watch?v=Loav1kbA640 . I've also studied the math about linear regression.

Day 1: 15th July 2018

I've created a python linear regressor with just Numpy and plot the greph with the training slope and interceppt.

Day 2: 16th July 2018

Svm classifier and kernel trick. Code needs to be improved.

Day 3: 17th July 2018

Improvements on svm model.

Day 4: 18th July 2018

I developed a K-Means classifier and posted it on GitHub.

Day 5: 19th July 2018

Some code cleaning on K-Means. I started studying Decision Trees and Random Forest.

Day 6: 20th July 2018

Day 7: 21th July 2018

Day 8: 22th July 2018

Day 9: 23th July 2018

Work:

Today I've watched the video 'Probability Theory - The Math of Intelligence #6' by Siraj Raval and with some other website I've built a simple Naive Bayes classifier.

Thoughts:

I have to apply it to real world data.

Link:

https://www.youtube.com/watch?v=PrkiRVcrxOs https://www.analyticsvidhya.com/blog/2017/09/naive-bayes-explained/ https://en.wikipedia.org/wiki/Naive_Bayes_classifier

Day 10: 24th July 2018

Work:

Performing Sentiment Analysis with a Naive Bayes model on review on books from the Amazon's platform.

Link:

http://jmcauley.ucsd.edu/data/amazon/

Day 11: 25th July 2018

Day 12: 26th July 2018

Day 13: 27th July 2018

Day 14: 28th July 2018

Day 15: 29th July 2018

Work:

Starting read the book "Deep Learning" by Ian Goodfellow et al.

Thoughts:

I have to understand deeply the math behind the model that I apply.

Link:

https://www.deeplearningbook.org/

Day 16: 30th July 2018

Work:

Studying some more Math on 'Deep Learning'.

Link:

Same of yesterday.

Day 17: 31th July 2018

Work:

Still studying math from 'Deep Learning'. Developing a spamm filter based on Naive Bayes classifier.

Thoughts:

I need more data preprocessing skills.

Link:

https://www.deeplearningbook.org/ https://www.kaggle.com/uciml/sms-spam-collection-dataset

Day 18: 1st August 2018

Work:

Watched some videos about Neural Network and backpropagation and starting developing a neural network with just NNumpy.

Thoughts:

Understaing ML concepts but still struggling with Python, I have to improve on this.

Link:

https://www.youtube.com/watch?v=h3l4qz76JhQ https://www.youtube.com/watch?v=q555kfIFUCM https://iamtrask.github.io/2015/07/12/basic-python-network/

Day 19: 2nd August 2018

Work:

After some problems, I finally managed to realize a NN with just Numpy, thanks to a post on TowardsDataScience. It's been difficult but very useful, now I want to try developing some other ML algorithm with classes in Python.

Thoughts:

while (code doesn't work): fix it

Link:

https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6

100daysofmlcode's People

Contributors

alessandropierro avatar

Watchers

 avatar  avatar

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.