Notes

deep learning pipeline#

Recall that a Neural Network follows the following construction:

1. Pass data (forward) through model to get predicted values
2. Calculate loss with predicted values against labels
3. Perform backpropagation w.r.t each weight / bias to get the direction in which to move that weight such that it moves closer to the global minima
4. Update parameters with gradients using an optimiser.

momentum#

ball’s pace slows down this makes total fkn sense! if the gradient signs are the same, increasing your confidence in that direction and move further. you want to take less steps over all

git checkout#

is deprecated.

git checkout --<file> will discard working tree changes.

recall that your working-tree is working-directory. similarly there is a staging area and a place to commit things.

finally, there is also the upstream repository that contains a copy of the code should shit go to fuck.

que

<figure><img src="https://ox-hugo.scripter.co/test/images/org-mode-unicorn-logo.png">
</figure>

He puts his claw against the divider. “Fist my bump.”

Andy Weir, Project Hail Mary

Read more >

setting the stage#

1. Mental Focus
2. Learn a programming language
3. Learn Data structures and algorithms
4. Complete Leetcode / programming practice
5. Software Engineering Concepts
6. Behavioural Practice
7. Best Methods of Applying
8. Interview Process & Internal Guidelines.

process for problem solving#

• always read the problem statement twice.
  • ask clarifying questions
• try think of different ways to solve the problem
• think end-to-end of the best solutions based on complexity
• write the algorithm from patterns in drawing
• code it out
• try and improve it once you think you’re finished.
• go through other solutions (even if you answered correctly)

problems#

arrays#

217. duplicate values | easy#

Given an integer array nums, return true if any value appears at least twice in the array, and return false if every element is distinct.