StudyDSA logoStudyDSA

Command Palette

Search for a command to run...

Sign InSign Up
Sign Up

Data StructuresAlgorithmsBig-O NotationSystem DesignMachine LearningRoboticsAI ResearchGlossary

Definition
StudyDSA

Where complexity meets clarity.
By Armas Zarra.

Topics

  • Data Structures
  • Algorithms
  • Big-O Notation
  • Robotics
  • AI Research
  • Machine Learning

Practice

  • Blind 75
  • LeetCode 75
  • NeetCode 150

Legal

  • Privacy Policy
  • Terms of Service

© 2026 Armas Films LLC

IntroductionMachine Learning

Machine Learning

How machines learn patterns from data instead of following hand-written rules.

Definition

Try writing rules that allow a program to recognize a cat in a photo. Pointy ears won't work because some breeds fold them flat, fur won't work because some cats barely have any, and whiskers match other animals too. You can't rely on rules because the task is inherently complex.


What if we don't write the rules but instead allow the computer to learn them? This is the core idea of machine learning. Instead of writing rules for the computer to apply to data, you show the computer all your data and allow it to create its own rules. The result is a model, or behavior learned from examples instead of heuristics.

Learning Path

I've curated the following topics in order, and they're everything I've learned from my time in school and the big-tech industry. You can jump around if you are confident in these topics, but I guarantee you will learn something new even on a simple topic. If you're new to machine learning, I urge you to explore these in order because I will build your understanding from the ground up.

Foundations

Almost everything in machine learning comes down to two questions. Can I measure how far apart things are? Then can I make the error go down? These topics are the "simplest," but they will help you understand the vocabulary, motivation, and just the core idea of what machine learning really is.

k-Nearest Neighbors

Predicts by asking the closest examples what they are.

Distance & Similarity

Euclidean, Manhattan, and cosine: three ways to say how alike two things are.

Coming soon!

Linear Regression

Fits a straight line through data to predict numbers.

Coming soon!

Multiple Linear Regression

The same line, drawn through many features at once.

x1x2x3w·xŷ
Coming soon!

Feature Scaling

Puts every feature on the same ruler so no single one drowns out the rest.

Coming soon!

Gradient Descent

How models learn: follow the error downhill, one step at a time.

Coming soon!

Stochastic Gradient Descent

Noisier steps from tiny batches, and epochs that finish in a fraction of the time.

Coming soon!

Logistic Regression

A linear model bent into predicting yes-or-no probabilities.

Coming soon!

Naive Bayes

Counts words like a spam filter and multiplies its way to a verdict.

freewinnowspam .92ham .08
Coming soon!
Evaluating Models

A model that scores well on its own training data is not very different from a student grading their own work. Evaluating a model's performance deserves its own section, which is why I've curated the following topics here. You may want to skip this and jump right into the "fun stuff," but I think you should give these topics some time. I even made it shorter and added just two.

Cross-Validation

Rotates which slice of data gets held out so every point takes a turn as the test.

Coming soon!

Classification Metrics

Precision, recall, and why 99% accuracy can still mean a useless model.

TPFPFNTN
Coming soon!
Classical ML

The algorithms that ran the field before deep learning, and still win on tabular data: clustering that finds groups no one labeled, trees that split their way to a decision, ensembles that turn many weak trees into one strong model, and the geometry of PCA and SVMs.

K-Means Clustering

Groups data around k center points without any labels.

Coming soon!

DBSCAN

Finds clusters by density, and calls the leftovers noise.

Coming soon!

Decision Trees

A flowchart of yes/no questions, learned from data.

Coming soon!

Random Forests

Hundreds of trees voting beat any single tree.

vote
Coming soon!

Gradient Boosting

Trees built one at a time, each fixing the last one's mistakes.

t1t2t3
Coming soon!

Support Vector Machines

Draws the widest possible gap between two classes.

Coming soon!

Principal Component Analysis

Squeezes many features into the few directions that matter most.

Coming soon!
Neural Networks

One neuron is just a weighted sum and a bend. The story of this tier is what happens when you stack them: forward propagation pushes a prediction through the layers, and backpropagation sends the blame backwards so every weight learns. Then come the tools that make training actually work: better optimizers, regularization, and knowing when to stop.

Perceptron

One neuron that learns AND but can never learn XOR.

Coming soon!

Activation Functions

The bends between layers, and the vanishing gradients they can cause.

Coming soon!

Forward Propagation

Multiply, add, squish, repeat: a prediction flowing through the layers.

Coming soon!

Backpropagation

The chain rule, applied backwards, that trains every network.

Coming soon!

Training a Neural Network

Epochs, shuffling, and knowing when the loss curve says stop.

Coming soon!

Softmax & Cross-Entropy

Turns raw scores into probabilities, then charges the model for being wrong.

Coming soon!

Optimizers: Momentum & Adam

Smarter steps than plain descent, tuned by the gradient's own history.

Coming soon!

Regularization: L2 & Dropout

Shrinks weights and silences random neurons so the network can't just memorize.

Coming soon!
Deep Learning & LLMs

The architectures built on that foundation. CNNs gave machines vision, recurrent networks and LSTMs gave them memory, and attention replaced memory with looking everything up at once. The tier ends at the transformer block and the tokenizer, which is where the AI Research page picks up.

Convolution

A small filter slides across the image and lights up where its pattern lives.

Coming soon!

CNN Architecture

Stack convolutions and pooling until pixels become a prediction.

cat
Coming soon!

Recurrent Neural Networks

Networks with memory, reading a sequence one step at a time.

Coming soon!

LSTM

Gates that choose what to remember, what to forget, and what to say.

Coming soon!

Word Embeddings

Turns words into vectors where distance means similarity.

catdogcar
Coming soon!

Attention

Every word looks at every other word and decides how much each one matters.

thecatsat
Coming soon!

The Transformer Block

Attention, a feed-forward layer, and residuals: the unit LLMs are stacks of.

attnffn
Coming soon!

Byte Pair Encoding

How text becomes tokens: merge the most common pair, then merge again.

lowlowlow
Coming soon!