Turmas
- CIC1205 – Aprendizado de Máquina (Pós-graduação)
- GCC1932 – Aprendizado de Máquina (Graduação)
Local/horário
- CEFET/RJ, Maracanã, Bloco E, 5o andar, sala 515
- Dia/horário: 5as-feiras, das 07h55 às 11h30
Visão geral
Aprendizado de Máquina (Machine Learning) é um campo de estudo da Inteligência Artificial cujo objeto de estudo são sistemas que podem aprender a realizar alguma tarefa por meio de experiências. Neste curso, o objetivo é apresentar uma introdução aos conceitos, modelos, métodos, técnicas e aplicações do Aprendizado de Máquina. São também apresentados alguns algoritmos pertencentes a diferentes famílias de métodos em AM (simbolistas, conexionistas, probabilísticos, baseados em proximidade).
Plano do curso
Documentos relevantes: plano do curso, calendário das graduações, calendário das pós-graduações.
| Date | Lecture |
| 20/03 | Course logistics (slides) ML overview (slides) Linear Regression (slides, notebook) |
| 27/03 | Logistic Regression (slides, notebook) Polynomial features (slides, notebook) Decision Tree Induction (slides, notebook) kNN (slides, notebook) |
| 03/04 | Model evaluation (slides, notebook, notebook) |
| 10/04 | Model selection (slides, notebook, notebook) |
| 17/04 | Imbalanced datasets (notebook) |
| 24/04 | Regularization (part I) (slides) |
| 08/05 | Model calibration (notebook) Model diagnostics (slides, notebook) |
| 15/05 | Model diagnostics (notebook) Ensemble Learning (slides) |
| 22/05 | Time Series Data (slides, notebook) Rolling Window (notebook) |
| 29/05 | Conformal Prediction (slides, notebook, notebook) Feature encoding (notebook) |
| 02/05 | Dimension Reduction (slides, notebook, notebook) |
| 05/06 | PyTorch basics (notebook) |
| 02/06 | Perceptron; backpropagation (notebook) |
| 26/06 | Multi-layer Perceptron (notebook) Convolutional Neural Nets – 2D (notebook) |
| TBD | Convolutional Neural Nets – 1D (notebook) Dropout & Early Stopping (notebook) |
| TBD | Word2Vec (slides, notebook) |
| TBD | Transformer Architecture (slides, notebook) |
| TBD | Reserved for discussion on practical projects |
| TBD | Presentation of practical projects |
Additional resources
- Video: Recurrent Neural Networks, Image Captioning, LSTM, Andrej Karpathy.
- Online course: Practical Deep Learning For Coders
- Online course: Neural Networks and Deep Learning
- Online course: (Codecademy) Learn Python
- Word Embeddings
- Representation Learning for Reading Comprehension
- Practical Generative Adversarial Networks for Beginners
Readings
- (r1) Tom Mitchel, Key Ideas in Machine Learning
- (r2) Pedro Domingos, A Few Useful Things to Know About Machine Learning
- (r3) Sebastian Raschka, Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning
- (r4) Eric Bauer & Ron Kohavi, An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants
- (r5) Matriz Factorization for Recommender Systems
- (r6) Empirical Analysis of Predictive Algorithms for Collaborative Filtering
Books
- Ani Adhikari & John DeNero, Artificial Intelligence: Foundations of Computational Agents, second edition, Cambridge University Press, 2017.
- Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition, 2019.
- Brett Lantz. Machine Learning with R . Packt Publishing, Birmingham, October 2013.
- Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2006. pdf github
- Ethen Alpaydin, Introduction to Machine Learning, MIT Press, 2010.
- Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani. An Introduction to Statistical Learning: with Applications in R . Springer, 1st ed. 2013. corr. 4th printing 2014
- Ian Goodfellow et al, Deep Learning, MIT Press, 2016.
- Jake VanderPlas, Python Data Science Handbook, 2016.
- Jeremy Watt et al, Machine Learning Refined: Foundations, Algorithms, and Applications
- Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. The MIT Press, Cambridge, MA, 1 edition edition, August 2012.
- Marc Peter et al, Mathematics for Machine Learning.
- Max Kuhn and Kjell Johnson, Feature Engineering and Selection: A Practical Approach for Predictive Models
- Peter Flach. Machine Learning: The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press, Cambridge ; New York, 1st edition, 2012.
- Sebastian Raschka, Python Machine Learning, 3rd ed, Packt Publishing, 2019.
- Simon O. Haykin. Neural Networks and Learning Machines . Prentice Hall, New York, 3 edition edition, November 2008.
- Tom Mitchell, Machine Learning, McGraw-Hill, 1997.
- Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin. Learning From Data . AMLBook, S.l., March 2012.
Livros de interesse geral sobre Aprendizado de Máquina
- Gary Marcus & Ernest Davis, Rebooting AI: Building Artificial Intelligence We Can Trust, 2019.
- Melanie Mitchel, Artificial Intelligence: A Guide for Thinking Humans, 2019.
- Jimmy Soni & Rob Goodman, A Mind at Play: How Claude Shannon Invented the Information Age, 2017.
- Pedro Domingos, The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World, 2015.
- Nick Bostrom, Superintelligence: Paths, Dangers, Strategies, 2014.