Probabilistic Graphical Models and Causal Inference Episode 3: Structural Causal Models (from Interventions to Counterfactuals) [pdf]
- Berkeley Admission test (path-specific) [xdsl]Probabilistic Graphical Models and Causal Inference Episode 2: Causal Graphical Models [pdf]
Examples with "GeNIe" (free academic version) available at BayesFusion llc [link]: - Berkeley Admission test [xdsl] - Berkeley Admission test (modified) [xdsl] - Berkeley dataset [csv]
Probabilistic Graphical Models and Causal Inference Episode 1: Probabilistic Graphical Models [pdf]
Deep Learning and TensorFlow - A Short Course, 2020 Episode 4, Part 1: TensorFlow Basics [pdf]
Deep Learning and TensorFlow - A Short Course, 2020 Episode 3: Deep Convolutional Neural Networks [pdf]
Deep Learning and TensorFlow - A Short Course, 2020 Episode 2: The Quest for Deeper Networks [pdf]
Deep Learning and TensorFlow - A Short Course, 2020 Episode 1: Artificial Neural Networks [pdf]
Deep Learning and TensorFlow - A Short Course, 2020 Detailed Syllabus [pdf]
Deep Learning and TensorFlow - A Short Course, 2019 Exercises for laboratory activity [BitBucket]
Deep Learning and TensorFlow - A Short Course, 2019 Episode 4: TensorFlow Basics - Part 1 [pdf] Episode 4: TensorFlow Basics - Part 2 [pdf]
Deep Learning and TensorFlow - A Short Course, 2019 Episode 3: Deep Convolutional Neural Networks [pdf]
Deep Learning and TensorFlow - A Short Course, 2019 Episode 2: The Quest for Deeper Networks [pdf]
Deep Learning and TensorFlow - A Short Course, 2019 Episode 1: Artificial Neural Networks [pdf]
Deep Learning and TensorFlow - A Short Course, 2019 Detailed Syllabus [pdf]
Deep Learning and TensorFlowA Short Course for PhD Students Submission of Project Proposals [pdf] Exercises for laboratory activity [BitBucket]
Deep Learning and TensorFlowA Short Course for PhD Students Episode 4: TensorFlow Basics - Part 1 [pdf] Episode 4: TensorFlow Basics - Part 2 [pdf]
Deep Learning and TensorFlow - A Short Course Episode 3: Deep Convolutional Neural Networks [pdf]
Deep Learning and TensorFlow - A Short Course Episode 2: The Quest for Deeper Networks [pdf]
Deep Learning and TensorFlow - A Short Course Episode 1: Artificial Neural Networks [pdf]
Deep Learning and TensorFlow - A Short Course Detailed Syllabus [pdf]
Marco Piastra [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
Smart inventory management: Will Deep Reinforcement Learning help us win the game? [pdf] In collaboration with Ariadne Srl An experimental application of Deep Reinforcement Learning (DRL) to a specific e-commerce problem.
Marco Piastra [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
Deep Learning: a theoretical introduction
A short course for PhD students.
Episode 3: a bag of wonderful tricks [pdf]
Deep Convolutional Neural Networks (DCNN);
basic principles and gradient computations; layer-oriented analysis; image generation; abstraction: what kind of information
is represented at each layer; variants and applications; Deep Learning for non-imaging applications.
Marco Piastra [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
Deep Learning: a theoretical introduction A short course for PhD students. Episode 2: the turning point [pdf] Probabilistic approach; undirected graphical model; Restricted Boltzmann Machine (RBM); Deep Boltzmann Machines (DBM); Deep Belief Network as an approximation to DBM; deep autoencoders and associative memory; generative model.
Marco Piastra [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
Deep Learning: a theoretical introduction
A short course for PhD students.
Episode 1: what we already knew [pdf]
A review the basic definitions for feed-forward neural networks; formal results related; potential advantages of deep network
architectures; ensuing problems for automatic learning.
Edoardo Maria Ponti [email]
Dipartimento di Studi Umanistici
Sezione di Linguistica Teorica e Applicata
Università degli Studi di Pavia
Machine Learning techniques applied to dependency parsing [pdf]
Andrea Pedrini [email]
Dipartimento di Matematica "Federigo Enriques"
Università degli Studi di Milano
The Hidden Topology of a Noisy Point Cloud (Part III) [pdf]
A critical reading of "Geometric Inference for Probability Measures" by Chazal, Steiner & Merigot, 2011.Andrea Pedrini [email]
Dipartimento di Matematica "Federigo Enriques"
Università degli Studi di Milano
The Hidden Topology of a Noisy Point Cloud (Part I) [pdf] and (Part II) [pdf]
A critical reading of "Geometric Inference for Probability Measures" by Chazal, Steiner & Merigot, 2011.Giacomo Parigi [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
Improving the Machine Interpretation of Internet Posts (Part II) [pdf]
Extraction of a lightweight, domain independent semantic network from the Wikipedia categorization system
Giacomo Parigi [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
Improving the Machine Interpretation of Internet Posts (Part I) [pdf]
Extraction of a lightweight, domain independent semantic network from the Wikipedia categorization system
Giulia Matrone [email]
Laboratorio di Bioingegneria 2
Università degli Studi di Pavia
Modeling and simulation of 3D ultrasound imaging systems with integrated micro-beamforming electronics [pdf]
Marco Piastra [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
The Connections: point clouds, offset, homotopy type, Delaunay complex,
critical function and all that… [pdf]
A few observations about the relevance of "The Hidden Topology of a Point Cloud" (see below)
for effective algorithms
Andrea Pedrini [email]
Dipartimento di Matematica "Federigo Enriques"
Università degli Studi di Milano
The Hidden Topology of a Point Cloud (Part II) [pdf]
Andrea Pedrini [email]
Dipartimento di Matematica "Federigo Enriques"
Università degli Studi di Milano
The Hidden Topology of a Point Cloud (Part I) [pdf]
Laura Brandolini [email]
Computer Vision and Multimedia Lab
Università degli Studi di Pavia
A Discrete Approach to Reeb Graph Computation and Surface Mesh Segmentation: Theory and Algorithm [pdf]
Mailing List & Forum
Marco Piastra