Topic outline

  • Intelligent Systems for Pattern Recognition - 9 CFU

    Code: 760AA, Credits (ECTS): 9, Semester: 2, Official Language: English

    Instructor: Davide Bacciu 

    Contact: email - phone 050 2212749

    Office: Room 367, Dipartimento di Informatica, Largo B. Pontecorvo 3, Pisa

    Office Hours: (email to arrange meeting)

  • Course Information

    Weekly Schedule

    The course is held on the second term. The tentative schedule for A.A. 2022/23 is provided in table below.

    The first lecture of the course will be ON FEBRUARY 21st 2023 h. 11.30 (note the slightly delayed starting time for only this lecture). The course will be hybrid, both in person and online on the dedicated MS Team.

    Recordings of the lectures will be made available to the students following the course.

    Day Time
    Tuesday 11.00-12.45 (Room C1, Online)
    Wednesday 16.15-18.00 (Room E, Online)
    Thursday 14.15-16.00 (Room C, Online)


    Objectives

    Course Prerequisites

    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.

    Course Overview

    The course introduces students to the analysis and design of advanced machine learning and deep learning models for modern pattern recognition problems and discusses how to realize advanced applications exploiting computational intelligence techniques.

    The course is articulated in five parts. The first part introduces basic concepts and algorithms concerning traditional 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,  their combinaton and their use in pattern recognition applications. The fourth part will introduce fundamentals of reinforcement learning and deep reinforcement learning. The final part of the course will present selected recent works, models and applications of learning 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.

    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.

    Topics covered -Bayesian learning, graphical models, learning with sampling and variational approximations, fundamentals of deep learning (CNNs, AE, DBN, GRNs), deep learning for machine vision and signal processing, advanced deep learning models (transformers, NTMs), generative deep learning (VAE, GANs, diffusion models, score-based models) deep graph networks, reinforcement learning and 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 programming libraries and frameworks.

    Textbooks 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 (PDF)

    [DL] Ian Goodfellow and Yoshua Bengio and Aaron Courville , Deep Learning, MIT Press (ONLINE)

    [RL] Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second Edition, MIT Press, 2018 (PDF)


  • Introduction (2h)

    Introduction to the course philosophy, its learning goals and expected outcomes. We will discuss prospectively the overall structure of the course and the interelations between its parts. Exam modalities and schedule are also discussed.
    Date Topic  References  
     Additional Material 
    1 21/02/2023
    (11.30-13)
    Introduction to the course
    Motivations and aim; course housekeeping (exams, timetable, materials); introduction to modern pattern recognition applications
    Remember to fill in your contact details here (by 24/02)

  • Fundamentals of Pattern Recognition (6h)

    The module will provide a brief introduction to classical pattern recognition for signal/timeseries and for images. We will cover approaches working on the spatial (temporal) and frequency (spectral) domain, presenting methods to represent temporal and visual information in static descriptors, as well as approaches to identify relevant patterns in the data (feature descriptors). Methodologies covered include correlation analysis, Fourier analysis, wavelets, intensity gradient-based descriptors and detectors, normalized cut segmentation.

    Date Topic  References  
     Additional Material 
    2
    22/02/2023
    (16-18)
    Signal processing
    Timeseries; time domain analysis (statistics, correlation); spectral analysis; fourier analysis.


    3 23/02/2023
    (14-16)
     Image Processing I
     Spatial feature descriptors (color histograms, SIFT); spectral analysis.
      Additional readings
     [1] Survey on visual descriptors

    Software:
    • A tweakable and fast implementation of SIFT in C (on top of OpenCV)
     4 01/03/2023
    (16-18)
     Image Processing II
     Feature detectors (edge, blobs); image segmentation; wavelet decompositions
     
    Additional readings 
    [2] Survey on visual feature detectors

    A reference book for the pattern recognition part is " S. THEODORIDIS, K. KOUTROUMBAS, Pattern Recognition, 4th edition". It is not needed for the sake of the course, but it is a reference book if you are interested on the topic. It is not available online for free (legally; what you do with Google is none of my business).

    You can find the original NCUT paper freely available from authors here.

    Software
    A wavelet browser to visualize some popular wavelet families and their instances, powered by the PyWavelet library.


  • Generative Learning

    The module introduces probabilistic learning, causal models, generative modelling and Bayesian learning. We will discuss fundamental algoritms and concepts, including Expectation-Maximization, sampling and variational approximations, and we will study relevant models from the three fundamental paradigms of probabilistic learning, namely Bayesian networks, Markov networks and dynamic models.  Models covered include: Bayesian Networks, Hidden Markov Models, Markov Random Fields, Boltzmann Machines,  Latent topic models.

    Bayesian Learning III
    sampling methods; ancestral sampling; Gibbs sampling and Monte Carlo methods

    Date Topic  References  
     Additional Material 
      5 
    02/03/2023
    (14-16)
    Introduction to Generative and Graphical Models.
    P
    robability refresher; graphical model representation; directed and undirected models
    [BRML] Ch. 1 and 2 (Refresher)
    [BRML] Sect. 3.1, 3.2 and 3.3.1
    (conditional independence)
    Software
    • 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
      6 
    03/03/2023
    (14-16)
    AULA E
    RECOVERY LECTURE

    Conditional independence and causality - Part I
    Bayesian networks; Markov networks; conditional independence;

    [BRML] Sect. 3.3 (Directed Models)
    [BRML] Sect. 4.1, 4.2.0-4.2.2 (Undirected Models)
    [BRML] Sect. 4.5 (Expressiveness)

     7  07/03/2023
    (11-13)
     Conditional independence and causality - Part II
    d-separation; structure learning in Bayesian Networks
    [BRML] Sect. 9.5.1 (PC algorithm)
    [BRML] Sect. 9.5.2 (Independence testing)
    [BRML] Sect. 9.5.3 (Structure scoring)
     Additional readings
    [3] A short review of BN structure learning
    [4] PC algorithm with consistent ordering for large scale data
    [5] MMHC - Hybrid structure learning algorithm

    If you are interested in deepening of your knowledge on causality this is an excellent book (also freely available online): Jonas Peters, Dominik Janzing, Bernhard Schölkopf, Elements of causal inference : foundations and learning algorithms, MIT Press.

    Software
    - A selection of BN structure learning libraries in Python: pgmpy, bnlearn, pomegranate.
    - bnlearn: the most consolidated and efficient library for BN structure learning (in R)
    - Causal learner: a mixed R-Matlab package integrating over 26 BN structure learning algorithms.
     8 08/03/2023
    (16-18) 
     Hidden Markov Models  - Part I
    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) 
     
     9  09/03/2023
    (14-16)
     Hidden Markov Models - Part II
    EM algorithm, learning as inference, Viterbi Algorithm
    [BRML] Sect. 23.2.6 (Viterbi)
    [BRML] Sect. 23.3.1-23.3.4 (EM and learning)
    Additional Readings
    [6]  A classical tutorial introduction to HMMs
     10 14/03/2023
    (11-13)
    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)
     Additional Readings
    [7,8] Two comprehensive tutorials on CRF ([7] more introductory and [8] more focused on vision)
    [9] A nice application of CRF to image segmentation

    Sofware
    Check out pgmpy: it has Python notebooks to introduce to working with MRF/CRF
     11 15/03/2023
    (16-18) 
    Bayesian Learning I
    Principles of Bayesian learning; EM algorithm objective; principles of variational approximation
    BRML] Sect. 11.2.1 (Variational EM)  
     12 16/03/2023
    (14-16) 
    Bayesian Learning II
    latent topic models; Latent Dirichlet Allocation; machine vision application of latent topic models
    [BRML] Sect. 20.4-20.6.1  (LDA)  Additional Readings
    [10] LDA foundation paper
    [11] A gentle introduction to latent topic models
    [12] Foundations of bag of words image representation

    Sofware
     13 21/03/2023
    (11-13)
     Bayesian Learning III
    sampling methods; ancestral sampling; Gibbs sampling and Monte Carlo methods
     [BRML] Sect. 27.1-27.3, 27.4.1, 27.6.2  Additional Readings
    [13] A step-by-step derivation of collapsed Gibbs sampling for LDA
     14 22/03/2023
    (16-18)
    Boltzmann Machines
    bridging neural networks and generative models; stochastic neuron; restricted Boltzmann machine; contrastive divergence
     [DL] Sections 20.1 and 20.2  Additional Readings
    [14] A clean and clear introduction to RBM from its author

    Sofware
    Matlab code for Deep Belief Networks (i.e. stacked RBM) and Deep Boltzmann Machines.

  • Deep Learning

    The module presents the fundamental concepts, challenges, architectures and methodologies of deep learning. We introduce the learning of neural representations from vectorial, sequential and image data, covering both supervised and unsupervised/generative learning, and hinting at various forms of weak supervision. We close the gap between neural networks and probabilistic learning by discussing generative deep learning models. Models covered include: deep autoencoders, convolutional neural networks, long-short term memory, gated recurrent units, deep reservoir computing, sequence-to-sequence, neural attention, neural Turing machines, variational autoencoders, generative adversarial networks. diffusion models, score-based methods. Methodological lectures will be complemented by introductory seminars to Keras-TF and Pytorch.

    Date Topic  References  
     Additional Material 
    15
    23/03/2023
    (14-16)
    Convolutional Neural Networks I
    Introduction to the deep learning module; i
    ntroduction to CNN; basic CNN elements
    [DL] Chapter 9
    Additional Readings
    [15-19] Original papers for LeNet, AlexNet, VGGNet, GoogLeNet and ResNet.
    16
    28/03/2023
    (11-13)
     Convolutional Neural Networks II
    CNN architectures for image recognition; convolution visualization; advanced topics (deconvolution, dense nets); applications and code
     [DL] Chapter 9 Additional Readings
    [20] Complete summary of convolution arithmetics
    [21] Seminal paper on batch normalization
    [22] CNN interpretation using deconvolutions
    [23] CNN interpretation with GradCAM
     17 29/03/2023
    (16-18)
    Deep Autoencoders
    S
    parse, denoising and contractive AE; deep RBM
    [DL] Chapter 14, Sect 20.3, 20.4.0 (from 20.4.1 onwards not needed) Additional Readings
    [24] DBN: the paper that started deep learning
    [25] Deep Boltzmann machines paper
    [26] Review paper on deep generative models
    [27] Long review paper on autoencoders from the perspective of representation learning
    [28] Paper discussing regularized autoencoder as approximations of likelihood gradient
     18 30/03/2023
    (14-16)
    Gated Recurrent Networks I
    Deep learning for sequence processing; gradient issues;
      [DL] Sections 10.1-10.3, 10.5-10.7, 10.10, 10.11  Additional Readings
    [29] Paper describing gradient vanish/explosion
    [30] Original LSTM paper
    [31] An historical view on gated RNN
     19 04/04/2023
    (11-13)
    Coding practice I - PyTorch
    Guest lecture by Danilo Numeroso
       
     20 05/04/2023
    (16-18) 
     Coding practice I - Tensorflow
    Guest lecture by Valerio De Caro
       
       06/04/2023-
    11/04/2023
     NO LECTURE: Easter Break
       

     21 12/04/2023
    (16-18) 
    Gated Recurrent Networks II
    long-short term memory; gated recurrent units; generative use of RNN
       Additional Readings
    [32] Gated recurren units paper
    [33] Seminal paper on dropout regularization

     Software
     22 13/04/2023
    (14-16)
    Advanced Recurrent Architectures I
    sequence-to-sequence;  attention models;
      [DL] Sections 10.12, 12.4.5  Additional Readings
    [34,35] Models of sequence-to-sequence and image-to-sequence transduction with attention
    [36] Transformer networks: a paper on the power of attention without recurrence
     23 14/04/2023
    (14-16)
    AULA E
    RECOVERY LECTURE
    Advanced Recurrent Architectures II
    multiscale network; hierarchical models; memory networks; neural Turing machines
       Additional Readings
    [37,38] Models optimizing dynamic memory usage (clockwork RNN, zoneout)
    [39] Differentiable memory networks
    [40,41] Neural Turing Machines and follow-up paper on pondering networks
     28  02/05/2023
    (11-13)
    Reservoir Computing
    Guest lecture by Andrea Ceni
       
       03-04/05/2023 NO LECTURE
       
     29  09/05/2023
    (11-13)
    Unsupervised and Generative Deep Learning I
    explicit distribution models; neural ELBO; variational autoencoders
     [DL] Sections 20.9, 20.10.1-20.10.3  Additional Readings
    [51] PixelCNN - Explict likelihood model
    [52] Tutorial on VAE

    Sofware
     30 10/05/2023
    (16-18)
    Unsupervised and Generative Deep Learning II
    generative adversarial networks; adversarial autoencoders
     [DL] Section 20.10.4  Additional Readings
    [53] Tutorial on GAN (here another online resource with GAN tips)
    [54] Wasserstein GAN
    [55] Tutorial on sampling neural networks
    [56] Progressive GAN
    [57] Cycle Gan
    [58] Seminal paper on Adversarial AEs

    Sofware
     31  11/05/2023
    (14-16)
    Unsupervised and Generative Deep Learning III
    diffusion models; latent space diffusion; conditional diffusion models
    [59] Introductory and survey paper on diffusion models
      Additional Readings
    [60] Seminal paper introducing diffusion models
    [61] An intepretation of diffusion models as score matching
    [62] Paper introducing the diffusion model reparameterization
    [63] Diffusion beats GAN paper
  • Reinforcement Learning (8h)

    We formalise the reinforcement learning problem by rooting it into Markov decision processes and we provide an overview of the main approaches to design reinforcement learning agents, including model-based, model-free, value and policy learning. We link classical approaches with modern deep learning based approximators (deep reinforcement learning). Methodologies covered include: dynamic programming, MC learning, TD learning, SARSA, Q-learning, deep Q-learning, policy gradient and deep policy gradient.


    Date Topic  References  
     Additional Material 
     24 18/04/2023
    (11-13)
    Reinforcement learning fundamentals & Model-Based Planning
    reinforcement learning problems; environment; agent; actions and policies; taxonomy of approaches; formal model of RL probelms; policy evaluation; policy iteration; value iteration
     [RL] Chapter 1, Chapter 3, Chapter 4
    Software
    • Open AI gym for RL environments and tasks
    • Dynamic programming demo on Gridworld in Javascript (with code)

     25 19/04/2023
    (16-18) 
     Model-free reinforcement learning
    model-free predition; model-free control; Monte Carlo methods; TD learning;  SARSA; Q-learning
     [RL] Section 5.1-5.6, 6.1-6.6, 7.1, 7.2, 12.1, 12.2, 12.7 Additional reading:
    [39] The original Q-learning paper
     26 20/04/2023
    (14-16) 
     Value-function Approximation
    linear incremental methods; batch value function approximation; deep Q-learning; linear least-squares control
     [RL] Section 9.1-9.5, 9.8, 10.1, 11.1-11.5  Additional Reading:
    [40] Original DQN paper
    [41] Double Q-learning
    [42] Dueling Network Architectures
    [43] Prioritized Replay
       25-27/04/2023
    NO LECTURES
       
     27 28/04/2023
    (14-16)
    AULA E

    RECOVERY LECTURE
    Policy gradient & Actor-Critic methods
     [RL] Chapter 13  Additional Reading:
    [44] Original REINFORCE paper
    [45] Learning with the actor-critic architecture
    [46] Accessible reference to natural policy gradient
    [47] A3C paper
    [48] Deep Deterministic Policy Gradient
    [49] TRPO paper
    [50] PPO paper

  • Advanced Topics and Applications (3h)

    The module covers some recent and interesting development and research topics in the field of machine learning. Topics choice is likely to vary at each edition. Example topics include: deep learning for graphs, continual learning, distributed learning, learning-reasoning integration, edgeAI,etc.. The module concludes with a final lecture which discusses the course content retrospectively and details the exam modalities, topics and deadlines.

       Date  Topic  References     Additional Material 
     32 16/05/2023
    (11-13)
     Deep learning for graphs

       Software
    - PyDGN: our in-house DLG library
    - PyTorch geometric
    - Deep graph library

    Additional readings
    [64-65] Seminal works on neural networks for graphs
    [66] Recent tutorial paper
     33 17/05/2023
    (16-18)
    Research seminars
    Algorithmic reasoning (Danilo Numeroso), continual learning (Andrea Cossu), graph reduction (Francesco Landolfi), causal learning (Riccardo Massidda), hyperparameters autotuning (Dario Balboni)

     
     34 18/05/2023
    (14-16)
     Final lecture
       

  • Course Grading and Exams

    Typical course examination (for students attending the lectures) is performed in 2 stages: midterm assignments and an oral exam. Midterms waive the final project.

    Midterm Assignment

    Midterms consist in short assignments involving with 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.

    The midterms can consist in either the delivery of code (e.g. colab notebook) or a short slide deck (no more than 10 slides) presenting the key/most-interesting aspects of the assignment. 

    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 3/4 weeks.

    Oral Exam

    The oral examination will test knowledge of the course contents (models, algorithms and applications).

    Exam Grading (with Midterms)

    The final exam vote is given by the oral grade. The midterms only wave the final project but do not contribute to the grade. In other words you can only fail or pass a midterm. You need to pass all midterms in order to succesfully wave the final project.

    Alternative Exam Modality (No Midterms / Non attending students)

    Working students, those not attending lectures, those who have failed midterms or simply do not wish to do them, can complete the course by delivering a final project and an oral exam.  Final project topics will be released in the final weeks of the course: contact the instructor by mail to arrange choice of the topics once these are published.

    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 15 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

     \( G = 0.5 \cdot (G_P + G_O) \)

    where \( G_P \in [1,32] \) is the project grade and \( G_O \in [1,30] \) is the oral grade

  • Midterms and Projects

  • Exams Schedule

    Exam Session I - 30/05/2023
    TIME PLACE NOTES
    07/06/2023
    h 09.30-11.30
     Room X2
     Polo Fibonacci
     Oral exam I
    09/06/2023
    h 09.30-11.30
     Room X2
     Polo Fibonacci
     Oral exam II

    Exam Session II - 20/06/2023
    TIME PLACE NOTES
    27/06/2023
    h.15-18
    Sala Polifunzionale - Dipartimento di informatica

    28/06/2023
    h.10-13
    Sala Polifunzionale - Dipartimento di informatica

    30/06/2023
    h.11-14
     Sala Riunioni Est - Dipartimento di informatica
     

    Exam Session III - 07/07/2023
    TIME PLACE NOTES
    17/07/2023
    h.14-16
    Sala Polifunzionale - Dipartimento di informatica

    18/07/2023
    h.10.30-13
    Sala Polifunzionale - Dipartimento di informatica


    Exam Session IV - 06/09/2023
    TIME PLACE NOTES
    13/09/2023
    h.9.30-11.30
    Sala Seminari Est - Dipartimento di informatica

    13/09/2023
    h.15.00-18
    Sala Seminari Est - Dipartimento di informatica


  • Bibliography

    Bibliographic References

    1. Scott Krigg, Interest Point Detector and Feature Descriptor Survey, Computer Vision Metrics, pp 217-282, Open Access Chapter
    2. 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
    3. C. Glymour, Kun Zhang and P. Spirtes, Review of Causal Discovery Methods Based on Graphical Models Front. Genet. 2019, Online version
    4. Bacciu, D., Etchells, T. A., Lisboa, P. J., & Whittaker, J. (2013). Efficient identification of independence networks using mutual information. Computational Statistics, 28(2), 621-646, Online version
    5. Tsamardinos, I., Brown, L.E. & Aliferis, C.F. The max-min hill-climbing Bayesian network structure learning algorithm. Mach Learn 65, 31–78 (2006), Online version
    6. 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
    7. Charles Sutton and Andrew McCallum,  An Introduction to Conditional Random Fields, Arxiv
    8. Sebastian Nowozin and Christoph H. Lampert, Structured Learning and Prediction, Foundations and Trends in Computer Graphics and Vision, Online Version
    9. Philipp Krahenbuhl, Vladlen Koltun, Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials, Proc.of NIPS 2011, Arxiv
    10. D. Blei, A. Y. Ng, M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Learning Research, 2003
    11. D. Blei. Probabilistic topic models. Communications of the ACM, 55(4):77–84, 2012, Free Online Version
    12. 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
    13. W. M. Darling, A Theoretical and Practical Implementation Tutorial on Topic Modeling and Gibbs Sampling, Lecture notes
    14. Geoffrey Hinton, A Practical Guide to Training Restricted Boltzmann Machines, Technical Report 2010-003, University of Toronto, 2010
    15. 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 Systems, NIPS, 1989
    16. A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, NIPS, 2012
    17. S. Simonyan and A. Zisserman.  Very deep convolutional networks for large-scale image recognition, ICLR 2015, Free Online Version
    18. C. Szegedy et al,  Going Deeper with Convolutions, CVPR 2015, Free Online Version
    19. K. He, X. Zhang, S. Ren, and J. Sun. Deep Residual Learning for Image Recognition. CVPR 2016, Free Online Version
    20. V. Dumoulin, F. Visin, A guide to convolution arithmetic for deep learning, Arxiv
    21. S. Ioffe, C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, ICML 2013,  Arxiv
    22. M.D. Zeiler and R. Fergus, Visualizing and Understanding Convolutional Networks, ICML 2013, Arxiv
    23. J. Adebayo et al, Sanity Checks for Saliency Maps, NeurIPS, 2018
    24. G.E. Hinton, R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks.Science 313.5786 (2006): 504-507, Free Online Version
    25. G.E. Hinton, R. R. Salakhutdinov. Deep Boltzmann Machines. AISTATS 2009, Free online version.
    26. R. R. Salakhutdinov. Learning Deep Generative Models, Annual Review of Statistics and Its Application, 2015, Free Online Version
    27. 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.
    28. G. Alain, Y. Bengio. What Regularized Auto-Encoders Learn from the Data-Generating Distribution, JMLR, 2014.
    29. Y. Bengio, P. Simard and P. Frasconi, Learning long-term dependencies with gradient descent is difficult. TNN, 1994, Free Online Version
    30. S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Computation, 1997, Free Online Version
    31. K. Greff et al, LSTM: A Search Space Odyssey, TNNLS 2016, Arxiv
    32. C. Kyunghyun et al, Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, EMNLP 2014, Arxiv
    33. N. Srivastava et al, Dropout: A Simple Way to Prevent Neural Networks from Overfitting, JLMR 2014
    34. Bahdanau et al, Neural machine translation by jointly learning to align and translate, ICLR 2015, Arxiv
    35. Xu et al, Show, Attend and Tell: Neural Image Caption Generation with Visual Attention, ICML 2015, Arxiv
    36. A. Vaswan et al, Attention Is All You Need, NIPS 2017, Arxiv
    37. Koutník et al, A Clockwork RNN, ICML 2014, Arxiv
    38. Krueger, Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activation, ICLR 2018, Arxiv
    39. CJCH Watkins, P Dayan, Q-learning, Machine Learning, 1992, PDF
    40. Mnih et al,Human-level control through deep reinforcement learning, Nature, 2015, PDF
    41. van Hasselt et al, Deep Reinforcement Learning with Double Q-learning, AAAI, 2015, PDF
    42. Wang et al, Dueling Network Architectures for Deep Reinforcement Learning, ICML, 2016, PDF
    43. Schaul et al, Prioritized Experience Replay, ICLR, 2016, PDF
    44. Williams, Simple statistical gradient-following algorithms for connectionist reinforcement learning, Machine Learning, 1992, PDF
    45. Sutton et al, Policy gradient methods for reinforcement learning with function approximation, NIPS, 2000, PDF
    46. Peters & Schaal, Reinforcement learning of motor skills with policy gradients, Neural Networks, 2008, PDF
    47. Mnih et al, Asynchronous methods for deep reinforcement learning, ICLR, 2016, PDF
    48. Lillicrap et al., Continuous control with deep reinforcement learning, ICLR, 2016, PDF
    49. Schulman et al, Trust Region Policy Optimization, ICML, 2015, PDF
    50. Schulman et al, Proximal Policy Optimization Algorithms, Arxiv
    51. A. van der Oord et al., Pixel Recurrent Neural Networks, 2016, Arxiv
    52. C. Doersch, A Tutorial on Variational Autoencoders, 2016, Arxiv
    53. Ian Goodfellow, NIPS 2016 Tutorial: Generative Adversarial Networks, 2016, Arxiv
    54. Arjovsky et al, Wasserstein GAN, 2017, Arxiv
    55. T. White, Sampling Generative Network, NIPS 2016, Arxiv
    56. T. Karras et al, Progressive Growing of GANs for Improved Quality, Stability, and Variation, ICLR 2018, Arxiv
    57. Jun-Yan Zhu et al, Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, ICCV 2017 Arxiv
    58. Alireza Makhzani et al, Adversarial Autoencoders, NIPS 2016, Arxiv
    59. Ling Yang et al, Diffusion Models: A Comprehensive Survey of Methods and Applications, 2023, Arxiv
    60. Jascha Sohl-Dickstein et al, Deep Unsupervised Learning using Nonequilibrium Thermodynamics, ICML 2015, PDF
    61. Y. Song & S. Ermon, Generative Modeling by Estimating Gradients of the Data Distribution, NeurIPS 2019, PDF
    62. Jonathan Ho et al, Denoising Diffusion Probabilistic Models, NeurIPS 2020, Arxiv
    63. P. Dhariwal & A. Nichol, Diffusion Models Beat GANs on Image Synthesis, NeurIPS 2021, PDF  
    64. A. Micheli, Neural Network for Graphs: A Contextual Constructive Approach. IEEE TNN, 2009, Online
    65. Scarselli et al, The graph neural network model, IEEE TNN, 2009, Online
    66. Bacciu et al, A Gentle Introduction to Deep Learning for Graphs, Neural Networks, 2020, Arxiv