Sveriges mest populära poddar

Machine Learning Guide

MLG 008 Math

28 min • 23 februari 2017

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

Full notes at ocdevel.com/mlg/8 

Mathematics in Machine Learning
  • Linear Algebra: Essential for matrix operations; analogous to chopping vegetables in cooking. Every step of ML processes utilizes linear algebra.
  • Statistics: The hardest part, akin to the cookbook; supplies algorithms for prediction and error functions.
  • Calculus: Used in the learning phase (gradient descent), similar to baking; it determines the necessary adjustments via optimization.
Learning Approach
  • Recommendation: Learn the basics of machine learning first, then dive into necessary mathematical concepts to prevent burnout and improve appreciation.
Mathematical Resources
  • MOOCs: Khan Academy - Offers Calculus, Statistics, and Linear Algebra courses.
  • Textbooks: Commonly recommended books for learning calculus, statistics, and linear algebra.
  • Primers: Short PDFs covering essential concepts.
Additional Resource
  • The Great Courses: Offers comprehensive video series on calculus and statistics. Best used as audio for supplementing primary learning. Look out for "Mathematical Decision Making."
Python and Linear Algebra
  • Tensor: General term for any dimension list; TensorFlow from Google utilizes tensors for operations.
  • Efficient computation using SimD (Single Instruction, Multiple Data) for vectorized operations.
Optimization in Machine Learning
  • Gradient descent used for minimizing loss function, known as convex optimization. Recognize keywords like optimization in calculus context.
Förekommer på
00:00 -00:00