Skip to main content
Computer Science

Machine Learning Study Guide

Supervised, unsupervised, and reinforcement learning — linear models, neural nets, evaluation, and modern deep learning.

Core topics in Machine Learning

  • Linear Regression and Classification
  • Decision Trees and Ensembles
  • Neural Networks
  • Backpropagation
  • Regularization
  • Evaluation Metrics
  • Unsupervised Learning
  • Transformers

Why students struggle

ML rewards understanding why methods work, not just how to call sklearn. Students who can fit models but can't diagnose failures (overfit, leakage, bad metric choice) stall in real projects.

How Fennie helps

Fennie generates diagnostic scenarios — given training curves and metrics, predict what's wrong before suggesting fixes.

How to study Machine Learning

  1. 01Implement linear regression and logistic regression from scratch once
  2. 02Master the bias-variance tradeoff with concrete examples
  3. 03Use Fennie for evaluation-metric selection problems
  4. 04Read papers — ML moves too fast for textbook-only study

Frequently asked questions

ML or data science?

ML focuses on methods and theory; data science emphasizes business application. Significant overlap.

Do I need linear algebra and stats?

Yes — both. Trying ML without them is rote sklearn-calling.

Does Fennie cover transformer architectures?

Yes — attention mechanisms, transformer blocks, and modern LLM intuition.

Start studying Machine Learning with Fennie

Upload your notes, syllabus, or textbook. Fennie builds a Daily Plan in under a minute and rebalances daily based on your performance.

Get started free

Other Computer Science subjects