Intelligent Systems for Pattern Recognition A.A. 2020-21 (ISPR)
- This topic
The course is held on the second term. The schedule for A.A. 2020/21 is provided in table below.
The first lecture of the course will be on Thursday 18/02/2021. The course will be offered online only due to the COVID19 pandemic. Lectures will be streamed following the schedule below by leveraging the dedicate MS Team accessible with this link.
Recordings of the lectures will be made available to the students following the course.
Day Time Thursday 14.15-16.00 Friday 11.00-12.45
Course prerequisites include knowledge of machine learning fundamentals (e.g. covered through ML course). Knowledge of elements of probability and statistics, calculus and optimization algorithms are also expected. Previous programming experience with Python is a plus for the practical lectures.
The course introduces students to the analysis and design of advanced machine learning models for modern pattern recognition problems and discusses how to realize advanced applications exploiting computational intelligence techniques.
The course is articulated in four parts. The first part introduces basic concepts and algorithms concerning pattern recognition, in particular as pertains sequence and image analysis. The next two parts introduce advanced models from two major learning paradigms, that are (deep) neural networks and generative models, and their use in pattern recognition applications. The last part will go into the details of the realization of selected recent applications of AI models. Presentation of the theoretical models and associated algorithms will be complemented by introductory classes on the most popular software libraries used to implement them.
The course hosts guest seminars by national and international researchers working on the field as well as by companies that are engaged in the development of advanced applications using machine learning models.
Topics covered - Bayesian learning, graphical models, deep learning models and paradigms, deep learning for machine vision and signal processing, advanced neural network models (recurrent, recursive, etc.), (deep) reinforcement learning, signal processing and time-series analysis, image processing, filters and visual feature detectors, pattern recognition applications (machine vision, bio-informatics, robotics, medical imaging, etc), introduction to machine learning and deep learning libraries.Textbook and Teaching Materials
The course does not have an official textbook covering all its contents. However, a list of reference books covering parts of the course is listed at the bottom of this section (note that all of them have an electronic version freely available online).
[BRML] David Barber, Bayesian Reasoning and Machine Learning, Cambridge University Press
[DL] Ian Goodfellow and Yoshua Bengio and Aaron Courville , Deep Learning, MIT Press
Lectures and Calendar
The official language of the course is English: all materials, references and books are in English.
Lecture slides will be made available here, together with suggested readings.
Date Room Topic References Additional Material 1 18/02/2021
ONLINE Introduction to the course: motivations and aim; course housekeeping (exams, timetable, materials); introduction to modern pattern recognition applications
ONLINE Signal processing: timeseries; time domain analysis (statistics, correlation); spectral analysis; fourier analysis.
ONLINE Image processing: feature descriptors (color histograms, SIFT), spectral analysis, feature detectors (edge, blobs and segments).
[1,2] Two high-level surveys on visual feature extraction and representation
ONLINE Generative and Graphical Models - Part 1: probability refresher; graphical model representation; directed and undirected models
[BRML] Ch. 1 and 2 (Refresher)
[BRML] Sect. 3.1, 3.2 and 3.3.1
ONLINE Generative and Graphical Models - Part 2: Bayesian networks; Markov networks; conditional independence and d-separation. [BRML] Sect. 3.3 (Directed Models)
[BRML] Sect. 4.1, 4.2.0-4.2.2 (Undirected Models)
[BRML] Sect. 4.5 (Expressiveness)
- Pyro - Python library based on PyTorch
- PyMC3 - Python library based on Theano
- Edward - Python library based on TensorFlow
- TensorFlow Probability - Probabilistic models and deep learning in Tensorflow
NO LECTURE DUE TO GRADUATION COMMITTEE (WILL BE RECOVERED) 6 11/03/2021
ONLINE Hidden Markov Models - Part 1: learning in directed graphical models; forward-backward algorithm; generative models for sequential data
[BRML] Sect. 23.1.0 (Markov Models)
[BRML] Sect. 23.2.0-23.2.4 (HMM and forward backward)
 A classical tutorial introduction to HMMs
ONLINE Hidden Markov Models - Part 2: EM algorithm, learning as inference, Viterbi Algorithm [BRML] Sect. 23.2.6 (Viterbi)
[BRML] Sect. 23.3.1-23.3.4 (EM and learning)
ONLINE Markov Random Fields: learning in undirected graphical models; conditional random fields; pattern recognition applications
[BRML] Sect. 4.2.2, 4.2.5 (MRF)
[BRML] Sect. 4.4 (Factor Graphs)
[BRML] Sect. 5.1.1 (Variable Elimination and Inference on Chain)
[BRML] Sect. 9.6.0, 9.6.1, 9.6.4, 9.6.5 (Learning in MRF/CRF)
[4,5] Two comprehensive tutorials on CRF ( more introductory and  more focused on vision)
 A nice application of CRF to image segmentation
Check out pgmpy: it has Python notebooks to introduce to working with MRF/CRF
ONLINE Boltzmann Machines: bridging neural networks and generative models; stochastic neuron; restricted Boltzmann machine; contrastive divergence
[DL] Sections 20.1 and 20.2 Additional Readings
 A clean and clear introduction to RBM from its author
Matlab code for Deep Belief Networks (i.e. stacked RBM) and Deep Boltzmann Machines.
ONLINE Bayesian Learning: non-parametric models; variational learning
[BRML] Sect. 11.2.1 (Variational EM), 20.4-20.6.1 (LDA) Additional Readings
 LDA foundation paper
 A gentle introduction to latent topic models
 Foundations of bag of words image representation
- A didactic Matlab demo of bag-of-words for images
- A standalone Matlab toolbox for latent topic models (including LDA examples, but discontinued) and the official Matlab LDA implementation
- A chatty demo on BOW image representation in Python
- Yet another Python implementation of image BOW
ONLINE Bayesian Learning: sampling methods - Guest lecture by Daniele Castellana
[BRML] Sect. 27.1-27.3, 27.4.1, 27.6.2 M1 30/03/2021
ONLINE Midterm 1 discussions 12 08/04/2021
ONLINE Convolutional Neural Networks (part I): introduction to CNN; basic CNN elements [DL] Chapter 9 Additional Readings
[11-15] Original papers for LeNet, AlexNet, VGGNet, GoogLeNet and ResNet.
ONLINE Convolutional Neural Networks (part II): CNN architectures for image recognition; convolution visualization; advanced topics (deconvolution, dense nets); applications and code
[DL] Chapter 9 Additional Readings
 Complete summary of convolution arithmetics
 Seminal paper on batch normalization
 CNN interpretation using deconvolutions
ONLINE Deep Autoencoders: introduction to the deep learning module, sparse, denoising and contractive AE; deep RBM
[DL] Chapter 14, Sect 20.3, 20.4.0 (from 20.4.1 onwards not needed) Additional Readings
 DBN: the paper that started deep learning
 Deep Boltzmann machines paper
 Review paper on deep generative models
 Long review paper on autoencoders from the perspective of representation learning
 Paper discussing regularized autoencoder as approximations of likelihood gradient
ONLINE Gated Recurrent Networks: deep learning for sequence processing; gradient issues; long-short term memory; gated recurrent units; generative use of RNN
[DL] Sections 10.1-10.3, 10.5-10.7, 10.10, 10.11 Additional Readings
 Paper describing gradient vanish/explosion
 Original LSTM paper
 An historical view on gated RNN
 Gated recurren units paper
 Seminal paper on dropout regularization
- A fun and high-level introduction to generative use of LSTM
- The up-to-date implementation of NeuraTalk
ONLINE Gated Recurrent Networks II 17 23/04/2021
ONLINE Deep randomized neural networks - Guest lecture by Claudio Gallicchio
ONLINE Learning in Structured Domain I: Recursive Neural Networks - Guest lecture by Alessio Micheli
ONLINE Learning in Structured Domain II: Neural Networks for Graphs - Guest lecture by Alessio Micheli
ONLINE Midterm 2 discussions 20 06/05/2021
ONLINE An introduction to Tensorflow and Keras: python; numpy, tensorflow, keras;
(Coding practice by Federico Errica)
ONLINE PyTorch – neural networks in Python: python; pytorch; RNN
(Coding practice by Antonio Carta)
ONLINE Advanced Recurrent Architectures: sequence-to-sequence; attention models; multiscale network; memory networks; neural reasoning.
[DL] Sections 10.12, 12.4.5 Additional Readings
[29,30] Models of sequence-to-sequence and image-to-sequence transduction with attention
[31,32] Models optimizing dynamic memory usage (clockwork RNN, zoneout)
 Differentiable memory networks
[34,35] Neural Turing Machines and follow-up paper on pondering networks
 Transformer networks: a paper on the power of attention without recurrence
ONLINE Generative and Unsupervised Deep Learning: explicit distribution models; variational autoencoders; adversarial learning.
[DL] Sections 20.9, 20.10.1-20.10.4 Additional Readings
 PixelCNN - Explict likelihood model
 Tutorial on VAE
 Tutorial on GAN (here another online resource with GAN tips)
 Wasserstein GAN
 Tutorial on sampling neural networks
- A tutorial on VAE with code
- Official Wasserstein GAN code
- Pixel-CNN code
- A (long) list of GAN models with (often) associated implementation
ONLINE Continual learning. Guest lecture by Vincenzo Lomonaco 25 21/05/2021
ONLINE Final lecture: course wrap-up; research themes; final projects; exam modalities
ONLINE Midterm 3 discussions
Course Grading and Exams
Typical course examination (for students attending the lectures) is performed in 2 stages: midterm assignments and an oral presentation. Midterms waive the final project.
Midterm assignments consist in a very short presentation (5 minutes per person) to be given in front of the class, presenting the key/most-interesting aspects of one of the following tasks:
- A quick and dirty (but working) implementation of a simple pattern recognition algorithm
- A report concerning the experience of installing and running a demo application realized using available deep learning and machine learning libraries
- A summary of a recent research paper on topics/models related to the course content.
Students might be given some amount of freedom in the choice of assignments, pending a reasonable choice of the topic. The assignments will roughly be scheduled every 1 month, with the last one being performed the day of the oral examination.
The oral examination will test knowledge of the course contents (models, algorithms and applications).
The final exam voteis determined as
- is the oral grade
Alternative Exam - Non attending students
Working students, those not attending lectures, those who have failed or are unsatisfied with midterms can complete the course by delivering a final project and an oral exam. Contact the instructor by mail to arrange project topics and examination dates.
The final project concerns preparing a report on a topic relevant to the course content or the realization of a software implementing a non-trivial learning model and/or a PR application relevant for the course. The content of the final project will be discussed in front of the instructor and anybody interested during the oral examination. Students are expected to prepare slides for a 20 minutes presentation which should summarize the ideas, models and results in the report. The exposition should demonstrate a solid understanding of the main ideas in the report.
Grade for this exam modality is determined as
whereis the project grade and is the oral grade
Midterms and Projects
- Scott Krigg, Interest Point Detector and Feature Descriptor Survey, Computer Vision Metrics, pp 217-282, Open Access Chapter
- Tinne Tuytelaars and Krystian Mikolajczyk, Local Invariant Feature Detectors: A Survey, Foundations and Trends in Computer Graphics and Vision, Vol. 3, No. 3 (2007) 177–2, Online Version
- Lawrence R. Rabiner:a tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 1989, pages 257-286, Online Version
- Charles Sutton and Andrew McCallum, An Introduction to Conditional Random Fields, Arxiv
- Sebastian Nowozin and Christoph H. Lampert, Structured Learning and Prediction, Foundations and Trends in Computer Graphics and Vision, Online Version
- Philipp Krahenbuhl, Vladlen Koltun, Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials, Proc.of NIPS 2011, Arxiv
- Geoffrey Hinton, A Practical Guide to Training Restricted Boltzmann Machines, Technical Report 2010-003, University of Toronto, 2010
- D. Blei, A. Y. Ng, M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Learning Research, 2003
- D. Blei. Probabilistic topic models. Communications of the ACM, 55(4):77–84, 2012, Free Online Version
- G. Csurka, C. R. Dance, L. Fan, J. Willamowski, and C. Bray. Visual Categorization with Bags of Keypoints. Workshop on Statistical Learning in Computer Vision. ECCV 2004, Free Online Version
- Y. LeCun, B. Boser, J.
S. Denker, D. Henderson, R. E. Howard, W. Hubbard and L. D. Jackel.
Handwritten digit recognition with a back-propagation network, Advances in Neural Information Processing
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, NIPS, 2012
- S. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition, ICLR 2015, Free Online Version
- C. Szegedy et al, Going Deeper with Convolutions, CVPR 2015, Free Online Version
- K. He, X. Zhang, S. Ren, and J. Sun. Deep Residual Learning for Image Recognition. CVPR 2016, Free Online Version
- V. Dumoulin, F. Visin, A guide to convolution arithmetic for deep learning, Arxiv
- S. Ioffe, C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, ICML 2013, Arxiv
- M.D. Zeiler and R. Fergus, Visualizing and Understanding Convolutional Networks, ICML 2013, Arxiv
- G.E. Hinton, R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks.Science 313.5786 (2006): 504-507, Free Online Version
- G.E. Hinton, R. R. Salakhutdinov. Deep Boltzmann Machines. AISTATS 2009, Free online version.
- R. R. Salakhutdinov. Learning Deep Generative Models, Annual Review of Statistics and Its Application, 2015, Free Online Version
- Y. Bengio, A. Courville, and P. Vincent. Representation learning: A review and new perspectives. Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 35(8) (2013): 1798-1828, Arxiv.
- G. Alain, Y. Bengio. What Regularized Auto-Encoders Learn from the Data-Generating Distribution, JMLR, 2014.
- Y. Bengio, P. Simard and P. Frasconi, Learning long-term dependencies with gradient descent is difficult. TNN, 1994, Free Online Version
- S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Computation, 1997, Free Online Version
- K. Greff et al, LSTM: A Search Space Odyssey, TNNLS 2016, Arxiv
- C. Kyunghyun
et al, Learning Phrase Representations using RNN
Encoder-Decoder for Statistical Machine Translation, EMNLP 2014, Arxiv
- N. Srivastava et al, Dropout: A Simple Way to Prevent Neural Networks from Overfitting, JLMR 2014
- Bahdanau et al, Neural machine translation
by jointly learning to align and translate, ICLR 2015, Arxiv
- Xu et al, Show, Attend and Tell: Neural Image Caption Generation with Visual Attention, ICML 2015, Arxiv
- Koutník et al, A Clockwork RNN, ICML 2014, Arxiv
- Krueger, Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activation, ICLR 2018, Arxiv
- Sukhbaatar et al, End-to-end Memory Networks, NIPS 2015, Arxiv
- A. Graves et al, Neural Turing Machines, Arxiv
- A.Graves, Adaptive Computation Time for Recurrent Neural Networks, Arxiv
- A. Vaswan et al, Attention Is All You Need, NIPS 2017, Arxiv
- A. van der Oord et al., Pixel Recurrent Neural Networks, 2016, Arxiv
- C. Doersch, A Tutorial on Variational Autoencoders, 2016, Arxiv
- Ian Goodfellow, NIPS 2016 Tutorial: Generative Adversarial Networks, 2016, Arxiv
- Arjovsky et al, Wasserstein GAN, 2017, Arxiv
- T. White, Sampling Generative Network, NIPS 2016, Arxiv
- Scott Krigg, Interest Point Detector and Feature Descriptor Survey, Computer Vision Metrics, pp 217-282, Open Access Chapter