<div dir="ltr"><div class="gmail_quote"><div dir="ltr"><div>Cari Dottorandi,</div><div><br></div><div>Vi segnaliamo questo corso di dottorato, che puo' essere seguito anche online.</div><div><br></div><div><div class="gmail_quote"><div dir="ltr" class="gmail_attr">---------- Forwarded message ---------<br>From: <strong class="gmail_sendername" dir="auto">Giacomo Boracchi</strong> <span dir="auto"><<a href="mailto:giacomo.boracchi@polimi.it" target="_blank">giacomo.boracchi@polimi.it</a>></span><br>Date: Tue, 26 Jan 2021 at 16:17<br>Subject: corso "Learning Sparse Representations for Image And Signal Modeling"<br>To: Stefano Gualandi <<a href="mailto:stefano.gualandi@unipv.it" target="_blank">stefano.gualandi@unipv.it</a>><br></div><br><div dir="ltr"><div>Quest'anno terrò la terza edizione del corso di dottorato "Learning Sparse Representations for Image and Signal Modeling", ne avevamo parlato e magari potrebbe interessare qualcuno dei vostri studenti.</div><div>Sarà anche streamed nella mia stanza Cisco Webex, quindi magari è ancora più comodo.</div><div><br>Il corso si articola in 6 lezioni da 4 ore ciascuna che comprendono sia una parte di spiegazione "tradizionale", sia una parte di "laboratorio" in Matlab in cui fornirò dei brevi codici da "riempire" nelle parti che riguardano gli algoritmi visti a lezione. <br><br>Sito:<br><a href="http://home.deib.polimi.it/boracchi/teaching/LearningSparse.htm" target="_blank">http://home.deib.polimi.it/boracchi/teaching/LearningSparse.htm</a><br>e <br><a href="https://www11.ceda.polimi.it/schedaincarico/schedaincarico/controller/scheda_pubblica/SchedaPublic.do?&evn_default=evento&c_classe=746348&polij_device_category=DESKTOP&__pj0=0&__pj1=8be18d617f9bbeab6cad76de3aed4947" target="_blank">https://www11.ceda.polimi.it/schedaincarico/schedaincarico/controller/scheda_pubblica/SchedaPublic.do?&evn_default=evento&c_classe=746348&polij_device_category=DESKTOP&__pj0=0&__pj1=8be18d617f9bbeab6cad76de3aed4947</a><br><br>*Calendario*:<br>- 09/02/2021 from 14:00 til 18:00 Sala Conferenze Emilio Gatti Ed. 20 - Piano Terra,<br>- 12/02/2021 from 14:00 til 18:00 Sala Conferenze Emilio Gatti Ed. 20 - Piano Terra,<br>- 16/02/2021 from 14:00 til 18:00 Sala Conferenze Emilio Gatti Ed. 20 - Piano Terra,<br>- 24/02/2021 from 14:00 til 18:00 Sala Conferenze Emilio Gatti Ed. 20 - Piano Terra,<br>- 26/02/2021 from 14:00 til 18:00 Sala Conferenze Emilio Gatti Ed. 20 - Piano Terra,<br>- 03/03/2021 from 14:00 til 19:00 Sala Conferenze Emilio Gatti Ed. 20 - Piano Terra,<br><br>*Subject of the course*<br>A large amount of multidisciplinary research has been conducted on sparse representations i.e., models that describe signals/images as a linear combination of a few atoms belonging to a dictionary. Sparse representation theory builds on a solid mathematical ground and has been applied in very diverse domains. Most importantly, these techniques nowadays represent one of the leading tools for solving ill-posed inverse problems in many areas, including image/signal processing, statistics, machine learning, computer vision, pattern recognition. In many cases, sparsity is a key technique to achieve state of the art performance in applications such as denoising, deconvolution, inpainting, superresolution, and some image classification problems. <br><br>The course presents the basic theory of sparse representations and dictionary learning, and illustrates the most successful applications of sparse models in imaging/signal processing. Particular emphasis will be given to modern proximal methods for solving convex optimization problems such as ℓ1 regularisation (e.g. BPDN, LASSO). Recent developments of sparse models will be also overviewed.<br><br>*Mission and Goals*<br>The main goal of this course is to provide the student with an understanding of the most important aspects of the theory underlying sparse representation and, more in general, of sparsity as a form of regularization in learning problems. Students will have the opportunity to develop and understand the main algorithms for:<br>1) learning sparse models,<br>2) computing sparse representations w.r.t. the learned model,<br>3) solve optimization problems involving sparsity as a regularization prior.<br><br>These methods have wide applicability in computer science, and these will be a useful background for their research.<br>In particular, this course aims at:<br>- Presenting the most important aspects of the theory underlying sparse representations, and in particular the sparse-coding and dictionary-learning problems.<br>- Illustrating the main algorithms for sparse coding and dictionary learning, with a particular emphasis on solutions of convex optimization problems that are widely encountered in engineering.<br>- Providing a broad overview of the applications involving sparse representations, in particular those in the imaging field.<br>- Providing students with a solid understanding of sparse representations by means of guided computer laboratory hours, where the presented algorithms will be implemented and tested in imaging applications.<br>- Providing an overview of sparsity as a general regularization prior and introduce recent developments such as convolutional sparsity<br><br>*Teaching Organization*<br>The course consists of traditional classes and computer-laboratory hours. During computer laboratory, students will be guided in the implementation of simplified versions of the presented algorithms. Imaging problems, including denoising, inpainting and anomaly detection, will be considered as running examples through the computer labs. Matlab is the preferred programming language (but you are of course allowed to use Python) and students are invited to work on their own laptop.<br><br>*Detailed course program follows:*<br><br>Basics on linear representations and vector spaces modeling<br>- Introduction: getting familiar with transform-domain representation and sparsity.<br>- Basic notions: linear representations, norms, orthonormal basis/projections, sparsity in a strict ℓ0 sense.<br>- Computer Lab: projection w.r.t. orthonormal basis, computing sparse solution. Introduce denoising as a running example.<br><br>Redundant representations and Sparse Coding (Minimum ℓ0 norm)<br>- Sparse Coding w.r.t redundant dictionaries Greedy Algorithms: Matching Pursuit, Orthogonal Matching Pursuit.<br>- Computer Lab: Greedy Sparse-Coding Algorithms<br>- An overview of theoretical guarantees and convergence results.<br><br>Convex Relaxation of the Sparse Coding Problem (Minimum ℓ1 norm)<br>- Sparse coding as a convex optimization problem, connections with ℓ0 solutions.<br>- BPDN and the LASSO, the two formulation and ℓ1 sparsity as a regularization prior in linear regression<br>- Other norms promoting sparsity: visual intuition. Theoretical guarantees.<br>- Minimum ℓ1 Sparse Coding Algorithms: Iterative Reweighted Least Squares, Proximal Methods, Iterative Soft Thresholding, ADMM.<br>- Computer Lab: Minimum ℓ1 Sparse Coding Algorithms <br><br>Dictionary Learning<br>- Dictionary Learning Algorithms: Gradient Descent, MOD, KSVD<br>- Task-Driven Dictionary Learning for Supervised learning tasks<br>- Computer Lab: Dictionary Learning <br><br>Structured Sparsity<br>- Joint Sparsity, Group Sparsity, Sparse Coding Algorithms, Group LASSO<br>- Extended Problems: Matrix Completion / Robust PCA<br>- Computer Lab: Structured Sparsity Algorithms<br><br>Extended sparse models<br>- Convolutional Sparsity and their connections with Convolutional Networks.<br>- Double Sparsity<br><br>Sparsity in engineering applications<br>- Relevant unsupervised learning problems involving sparsity as a regularization prior: Image Denoising, Inpainting, Superresolution, Deblurring.<br>- Supervised learning problems by Dictionary Learning and Sparse Coding: Classification and Anomaly Detection<br>- Computer Lab: Classification and Anomaly Detection in images <br clear="all"><div><br></div>-- <br><div dir="ltr" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div>Giacomo Boracchi, PhD<br>Dipartimento Elettronica, Informazione e Bioingegneria<br>DEIB, Politecnico di Milano<br>Via Ponzio, 34/5 20133 Milano, Italy.<br><br><a href="https://boracchi.faculty.polimi.it/" target="_blank">https://boracchi.faculty.polimi.it/</a><br></div></div></div></div></div></div></div>
</div></div></div>
</div><br clear="all"><div><br></div></div>