I started Standford's machine learning course but after getting stuck in one assignment (ex4, Week5), it fell of the table due to lack of time and focus.

I will use this Hack Week to make some progress on it.

Day 1

  • Studied back-propagation algorithm again, starting Week 5 from scratch

Day 2

  • Focused in the homework itself, understanding what I did last time.
  • Cross checked vector dimensions, to understand better
  • Simplified the code by vectorizing the second part the whole thing
  • Solved a mystery with dimensions realizing that in order to calculate δ2, I need to ignore the first column of Θ2 (bias)
  • Some progress

                                     Part Name |     Score | Feedback
                                     --------- |     ----- | --------
                 Feedforward and Cost Function |  30 /  30 | Nice work!
                     Regularized Cost Function |  15 /  15 | Nice work!
                              Sigmoid Gradient |   5 /   5 | Nice work!
     Neural Network Gradient (Backpropagation) |  40 /  40 | Nice work! 
                          Regularized Gradient |   0 /  10 |
                                     --------------------------------
                                               |  90 / 100 |
    
  • Working now on the regularized gradient. Homework additional material was helpful to understand the restriction of j=0

                                     Part Name |     Score | Feedback
                                     --------- |     ----- | --------
                 Feedforward and Cost Function |  30 /  30 | Nice work!
                     Regularized Cost Function |  15 /  15 | Nice work!
                              Sigmoid Gradient |   5 /   5 | Nice work!
     Neural Network Gradient (Backpropagation) |  40 /  40 | Nice work!
                          Regularized Gradient |  10 /  10 | Nice work!
                                     --------------------------------
                                               | 100 / 100 |
    
  • Continued with Week 6

    • Model Selection
    • Ways to diagnose bias vs variance by separating data into cross-validation and test sets

Day 3

  • Used on another Hackweek project

Day 4

  • Continued with model selection and bias/variance vs other parameters

Day 5

  • Finished Week 6 material. Debugging models and strategies to attack high bias or high variance
  • Quiz for Week 6. 100%
  • Started homework (ex5)
  • Implemented Regularized Linear Regression Cost Function and Regularized Linear Regression Gradient

Looking for hackers with the skills:

machinelearning learning

This project is part of:

Hack Week 19

Activity

  • over 5 years ago: dmacvicar added keyword "machinelearning" to this project.
  • over 5 years ago: dmacvicar added keyword "learning" to this project.
  • over 5 years ago: dmacvicar started this project.
  • over 5 years ago: dmacvicar originated this project.

  • Comments

    Be the first to comment!

    Similar Projects

    Advent of Code: The Diaries by amanzini

    Description

    It was the Night Before Compile Time ...

    Hackweek 25 (December 1-5) perfectly coincides with the first five days of Advent of Code 2025. This project will leverage this overlap to participate in the event in real-time.

    To add a layer of challenge and exploration (in the true spirit of Hackweek), the puzzles will be solved using a non-mainstream, modern language like D, Crystal, Gleam or Zig.

    The primary project intent is not just simply to solve the puzzles, but to exercise result sharing and documentation. I'd create a public-facing repository documenting the process. This involves treating each day's puzzle as a mini-project: solving it, then documenting the solution with detailed write-ups, analysis of the language's performance and ergonomics, and visualizations.

                                   |
                                 \ ' /
                               -- (*) --
                                  >*<
                                 >0<@<
                                >>>@<<*
                               >@>*<0<<<
                              >*>>@<<<@<<
                             >@>>0<<<*<<@<
                            >*>>0<<@<<<@<<<
                           >@>>*<<@<>*<<0<*<
             \*/          >0>>*<<@<>0><<*<@<<
         ___\\U//___     >*>>@><0<<*>>@><*<0<<
         |\\ | | \\|    >@>>0<*<0>>@<<0<<<*<@<<
         | \\| | _(UU)_ >((*))_>0><*<0><@<<<0<*<
         |\ \| || / //||.*.*.*.|>>@<<*<<@>><0<<<
         |\\_|_|&&_// ||*.*.*.*|_\\db//_
         """"|'.'.'.|~~|.*.*.*|     ____|_
             |'.'.'.|   ^^^^^^|____|>>>>>>|
             ~~~~~~~~         '""""`------'
    ------------------------------------------------
    This ASCII pic can be found at
    https://asciiart.website/art/1831
    
    

    Goals

    Code, Docs, and Memes: An AoC Story

    • Have fun!

    • Involve more people, play together

    • Solve Days 1-5: Successfully solve both parts of the Advent of Code 2025 puzzles for Days 1-5 using the chosen non-mainstream language.

    • Daily Documentation & Language Review: Publish a detailed write-up for each day. This documentation will include the solution analysis, the chosen algorithm, and specific commentary on the language's ergonomics, performance, and standard library for the given task.