Sveriges mest populära poddar

Machine Learning Guide

MLG 004 Algorithms - Intuition

23 min • 12 februari 2017

Try a walking desk to stay healthy while you study or work!

Show notes at ocdevel.com/mlg/4

The AI Hierarchy
  • Artificial Intelligence is divided into subfields such as reasoning, planning, and learning.
  • Machine Learning is the learning subfield of AI.
  • Machine learning consists of three phases:
    1. Predict (Infer)
    2. Error (Loss)
    3. Train (Learn)
Core Intuition
  • An algorithm makes a prediction.
  • An error function evaluates how wrong the prediction was.
  • The model adjusts its internal weights (training) to improve.
Example: House Price Prediction
  • Input: Spreadsheet with features like bedrooms, bathrooms, square footage, distance to downtown.
  • Output: Predicted price.
  • The algorithm iterates over data, learns patterns, and creates a model.
  • A model = algorithm + learned weights.
  • Features = individual columns used for prediction.
  • Weights = coefficients applied to each feature.
  • The process mimics algebra: rows = equations, entire spreadsheet = matrix.
  • Training adjusts weights to minimize error.
Feature Types
  • Numerical: e.g., number of bedrooms.
  • Nominal (Categorical): e.g., yes/no for downtown location.
  • Feature engineering can involve transforming raw inputs into more usable formats.
Linear Algebra Connection
  • Machine learning uses linear algebra to process data matrices.
  • Each row is an equation; training solves for best-fit weights across the matrix.
Categories of Machine Learning 1. Supervised Learning
  • Algorithm is explicitly trained with labeled data (e.g., price of a house).
  • Examples:
    • Regression (predicting a number): linear regression
    • Classification (predicting a label): logistic regression
2. Unsupervised Learning
  • No labels are given; the algorithm finds structure in the data.
  • Common task: clustering (e.g., user segmentation for ads).
  • Learns patterns without predefined classes.
3. Reinforcement Learning
  • Agent takes actions in an environment to maximize cumulative reward.
  • Example: mouse in a maze trying to find cheese.
  • Includes rewards (+points for cheese) and penalties (–points for failure or time).
  • Learns policies for optimal behavior.
  • Algorithms: Deep Q-Networks, policy optimization.
  • Used in games, robotics, and real-time decision systems.
Terminology Recap
  • Algorithm: Code that defines a learning strategy (e.g., linear regression).
  • Model: Algorithm + learned weights (trained state).
  • Features: Input variables (columns).
  • Weights: Coefficients learned for each feature.
  • Matrix: Tabular representation of input data.
Learning Path and Structure
  • Machine learning is a subfield of AI.
  • Machine learning itself splits into:
    • Supervised Learning
    • Unsupervised Learning
    • Reinforcement Learning
  • Each category includes multiple algorithms.
Resources
Förekommer på
00:00 -00:00