Difference between revisions of "Books"

From Research management course
Jump to: navigation, search
Line 2: Line 2:
  
 
Education in Machine learning has changed drastically in recent years. The main roadstones were deep learning, reinforcement learning, and now it is physics-informed or geometric deep learning. The requirements for mathematical knowledge rise, even for engineering parts. An example is differential programming techniques. Below we present bachelor and master programs for modern Machine learning. We call it Knowledge-aware machine learning.
 
Education in Machine learning has changed drastically in recent years. The main roadstones were deep learning, reinforcement learning, and now it is physics-informed or geometric deep learning. The requirements for mathematical knowledge rise, even for engineering parts. An example is differential programming techniques. Below we present bachelor and master programs for modern Machine learning. We call it Knowledge-aware machine learning.
 +
 +
<!--
 +
==Mathematics==
 +
Discrete analysis and graphs
 +
Abstract algebra and group theory
 +
Mathematical and functional analysis
 +
ODE, PDE, and mathematical modeling
 +
Measure and Probability
 +
 +
Linear algebra
 +
Tensor algebra and calculus
 +
Theoretical physics
 +
Differential geometry
 +
Scientific computation and numerical methods
 +
 +
Multivariate statistics
 +
Bayesian statistics and Graphical models
 +
Stochastic processes and SDE
 +
Bayesian model selection
 +
 +
Computer science courses
 +
Programming
 +
Software architectures
 +
System analysis
 +
Category theory
 +
Parallel and distributed computing
 +
 +
==Optimization and Control==
 +
Discrete optimization
 +
Convex optimization
 +
Mathematical programming
 +
 +
==Core Data Science ==
 +
Machine learning and data analysis
 +
Deep learning
 +
Generative models
 +
Reinforcement and online learning
 +
Geometric deep learning
 +
 +
==Applied Data Science==
 +
Signal analysis
 +
Computer vision
 +
Audio processing
 +
Topic modeling and Information retrieval
 +
Recommendation systems
 +
Multimedia and heterogeneous data
 +
Bioinformatics
 +
Brain-computer interfaces and metaverse
 +
 +
*** essential, ** recommended, * advanced
 +
 +
-->
 +
 +
  
 
==Machine learning for beginners==
 
==Machine learning for beginners==

Revision as of 00:12, 21 February 2023

Data Science: A Roadmap for Bachelor, Master, and Doctoral Degrees

Education in Machine learning has changed drastically in recent years. The main roadstones were deep learning, reinforcement learning, and now it is physics-informed or geometric deep learning. The requirements for mathematical knowledge rise, even for engineering parts. An example is differential programming techniques. Below we present bachelor and master programs for modern Machine learning. We call it Knowledge-aware machine learning.



Machine learning for beginners

Linear algebra

Optimization

Basics of probability and statistics

  • A first course in probability by Sheldon M. Ross, 2012
  • Elements of information theory by Thomas M. Cover, Joy A. Thomas, 2006
  • Probability theory by Alexandr A. Borovkov, 2006
  • Mathematical statistics by Alexandr A. Borovkov, 1999
  • Linear Statistical Inference & Its Applications by C. Radhakrishna Rao, 1967
  • Linear Models and Generalizations: Least Squares and Alternatives by C. Radhakrishna Rao et al., 2007

Bayesian statistics and inference

Functional data analysis

Discrete analysis

  • Lectures on discrete geometry by Jiří Matoušek, 2002
  • Indiscrete thoughts by Gian-Carlo Rota, 2008
  • Graph theory by Reinhard Diestel, 2017
  • Graph theory (groups and symmetries: from finite groups to Lie groups) by Reinhard Diestel, 2000

Programming

Ru

Retrieved from ‘https://m1p.org/index.php?title=Books&oldid=1145’