Machine Learning Refined

Machine Learning Refined

by Watt, Jeremy

Type Book
Rate 0.0 /5

Providing a unique approach to machine learning, this text contains fresh and intuitive, yet rigorous, descriptions of all fundamental concepts necessary to conduct research, build products, tinker, and play. By prioritizing geometric intuition, algorithmic thinking, and practical real world applications in disciplines including computer vision, natural language processing, economics, neuroscience, recommender systems, physics, and biology, this text provides readers with both a lucid understan…

Read More ↓
Details
Files
Reviews
Download

Title Statements

  • Full title :Machine Learning Refined.

Summary

Providing a unique approach to machine learning, this text contains fresh and intuitive, yet rigorous, descriptions of all fundamental concepts necessary to conduct research, build products, tinker, and play. By prioritizing geometric intuition, algorithmic thinking, and practical real world applications in disciplines including computer vision, natural language processing, economics, neuroscience, recommender systems, physics, and biology, this text provides readers with both a lucid understanding of foundational material as well as the practical tools needed to solve real-world problems. with in-depth Python and MATLAB/OCTAVE-based computational exercises and a complete treatment of cutting edge numerical optimization techniques, this is an essential resource for students and an ideal reference for researchers and practitioners working in machine learning, computer science, electrical engineering, signal processing, and numerical optimization.

Read More ↓

Edition Statements

  • Publication Date:2016.

Publication Statements

Notes

5.1.4 Common bases for continuous function approximation.

The Physical Object

  • Description:1 online resource (302 pages)

Edition Identifiers

  • ISBN:9781316402276, 1316402274
  • oclc:ocn961063986
  • LC Classification:Q325.5
  • Dewey Decimal:006.3/1

Table of Contents

Cover; Half-title page; Title page; Copyright page; Contents; Preface; 1 Introduction; 1.1 Teaching a computer to distinguish cats from dogs; 1.1.1 The pipeline of a typical machine learning problem; 1.2 Predictive learning problems; 1.2.1 Regression; 1.2.2 Classification; 1.3 Feature design; 1.4 Numerical optimization; 1.5 Summary; Part I Fundamental tools and concepts; 2 Fundamentals of numerical optimization; 2.1 Calculus-defined optimality; 2.1.1 Taylor series approximations; 2.1.2 The first order condition for optimality; 2.1.3 The convenience of convexity.

2.2 Numerical methods for optimization2.2.1 The big picture; 2.2.2 Stopping condition; 2.2.3 Gradient descent; 2.2.4 Newton's method; 2.3 Summary; 2.4 Exercises; 3 Regression; 3.1 The basics of linear regression; 3.1.1 Notation and modeling; 3.1.2 The Least Squares cost function for linear regression; 3.1.3 Minimization of the Least Squares cost function; 3.1.4 The efficacy of a learned model; 3.1.5 Predicting the value of new input data; 3.2 Knowledge-driven feature design for regression; 3.2.1 General conclusions; 3.3 Nonlinear regression and l[sub(2)] regularization.

3.3.1 Logistic regression3.3.2 Non-convex cost func…

Read More ↓

Subjects

Apprentissage automatique Machine learning

Writers

Watt, Jeremy Borhani, Reza Katsaggelos, Aggelos

Rate & Review

0.0/5
(0 people Voted)

No reviews yet. Be the first to rate this work.

Files & Downloads

  • Machine Learning Refined: Foundations, Algorithms…

    AZW3 · 6.6 MB · updated
    Login →

  • Machine Learning Refined: Foundations, Algorithms…

    EPUB · 6.1 MB · updated
    Login →

  • Machine Learning Refined: Foundations, Algorithms…

    PDF · 30.9 MB · updated
    Login →

  • Machine Learning Refined: Foundations, Algorithms…

    PDF · 27.9 MB · updated
    Login →

  • Machine learning refined foundations, algorithms,…

    PDF · 7.8 MB · updated
    Login →
Log in to request a copy