Computer Engineering is coming soon

We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.

Computer Engineering

Optimization in Machine Learning

Gradient and Newton methods, stochastic and evolution strategies, convex optimisation, genetic algorithms, PSO and ant colonies.

Interview questions
Notes for Optimization in Machine Learning are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.

Coming next in Optimization in Machine Learning

  1. Classification of optimisation problems· notes coming
  2. Types of optima· notes coming
  3. Convex objective functions· notes coming
  4. Gradient descent and conjugate gradient· notes coming
  5. Momentum and adaptive methods· notes coming
  6. Newton's method· notes coming
  7. Noisy descent and direct search· notes coming
  8. Cross-entropy method· notes coming
  9. Evolution strategies and CMA-ES· notes coming
  10. Convex optimisation problems· notes coming
  11. Linear and quadratic programming· notes coming
  12. Geometric programming· notes coming
  13. Evolutionary algorithms· notes coming
  14. Selection operators· notes coming
  15. Canonical genetic algorithm· notes coming
  16. Particle swarm optimisation· notes coming
  17. Ant colony optimisation· notes coming
  18. Vector spaces, matrices and eigenvalues for optimisation· notes coming
  19. Quadratic forms and matrix norms· notes coming
  20. One-dimensional search: golden section and Fibonacci· notes coming
  21. Secant method· notes coming
  22. Simplex method and duality· notes coming
  23. Equality and inequality constraints· notes coming
  24. Karush–Kuhn–Tucker conditions· notes coming
  25. Projected gradient methods· notes coming
  26. Penalty methods· notes coming