Teaching - Università Roma Tre

FM530 - Mathematical Methods for Machine Learning (objectives)

Code

20410875

Language

ITA

Type of certificate

Profit certificate

Credits

9

Scientific Disciplinary Sector Code

MAT/07

Contact Hours

48

Exercise Hours

24

Type of Activity

Core compulsory activities

Teacher	TERESI LUCIANO (syllabus) Highlights of Linear Algebra: Matrix-matrix multiplication; column & row space; rank The four fundamental subspaces of linear algebra Fundamentals of Matrix factorizations: A=LU rows & columns point of view A=LU elimination & factorization; permutations A=RU=VU; Orthogonal matrices Eigensystems and Linear ODE Intro to PSym; the energy function Gradient and Hessian Singular Value Decomposition Eckart-Young; derivative of a matrix norm Principal Component Analysis Generalized evectors; Norms Least Squares Convexity & Newton’s method Newton & L-M method; Recap of non-linear regression Lagrange multipliers Machine Learning: Gradient Descend; exact line search; GD in action; GD with Matlab Learning & Loss; Intro to Deep Neural Network; DNN with Matlab Loss functions: Quadratic VS Cross entropy Stocastics Gradient Descend (SGD) & Kaczmarcz; SGD convergence rates & ADAM Matlab interface for DNN Construction of DNN: the key steps Backpropagation and the Chain Rule Machine Learning examples with Wolfram Mathematica Convolutional NN + Mathematica examples of 1D convolution Convolution and 2D filters + Mathematica examples of 2D convolution Matlab Live Script, Network Designer, Pretrained Net (reference books) Lecture notes
Dates of beginning and end of teaching activities	From to
Delivery mode	Traditional At a distance
Attendance	not mandatory
Evaluation methods	Oral exam A project evaluation

Teacher	GIULIANI ALESSANDRO (syllabus) Highlights of Linear Algebra: Matrix-matrix multiplication; column & row space; rank The four fundamental subspaces of linear algebra Fundamentals of Matrix factorizations: A=LU rows & columns point of view A=LU elimination & factorization; permutations A=RU=VU; Orthogonal matrices Eigensystems and Linear ODE Intro to PSym; the energy function Gradient and Hessian Singular Value Decomposition Eckart-Young; derivative of a matrix norm Principal Component Analysis Generalized evectors; Norms Least Squares Convexity & Newton’s method Newton & L-M method; Recap of non-linear regression Lagrange multipliers Machine Learning: Gradient Descend; exact line search; GD in action; GD with Matlab Learning & Loss; Intro to Deep Neural Network; DNN with Matlab Loss functions: Quadratic VS Cross entropy Stocastics Gradient Descend (SGD) & Kaczmarcz; SGD convergence rates & ADAM Matlab interface for DNN Construction of DNN: the key steps Backpropagation and the Chain Rule Machine Learning examples with Wolfram Mathematica Convolutional NN + Mathematica examples of 1D convolution Convolution and 2D filters + Mathematica examples of 2D convolution Matlab Live Script, Network Designer, Pretrained Net (reference books) Lecture notes
Dates of beginning and end of teaching activities	From to
Delivery mode	Traditional At a distance
Attendance	not mandatory
Evaluation methods	Oral exam A project evaluation