Aula 01 – Introdução ao Aprendizado de Máquina; Regressão Linear (uma variável)
- Microsoft: AI Isn’t Yet Adaptable Enough to Help Businesses
Why Machines Still Can’t Learn So Good - Image Recognition: A Short History and All You Need to Know About It
- Informações sobre Arthur Samuel: aqui e aqui
- Informações sobre Tom Mitchell
- Whoever Controls Machine Learning Controls The Future
- Is AI Riding a One-Trick Pony? (September 29, 2017)
Aula 02 – Regressão Linear (várias variáveis); Regressão Logística
- Derivação apresentada em aula do função hipótese para a regressão logística
- Derivação da função de custo para a regressão logística
- Outra versão da derivação da função de custo para a regressão logística
- Texto introdutório sobre regressão logística
- Tutorial: Python
Aula 03 – Regularização; Refinamento de Algoritmos de Aprendizado de Máquina
- Stupid Data Miner Tricks (texto com descrição acerca do sobreajuste)
- Quora: What is Regularization in ML?
- Overfitting and Underfitting With Machine Learning Algorithms
- Overfitting: when accuracy measure goes wrong
- Explicação acerca de não ser necessária a regularização de theta_0
- Understanding the Bias-Variance Tradeoff
- Accurately Measuring Model Prediction Error
- Validation Error less than training error?
- Model evaluation, model selection, and algorithm selection in machine learning
- Thoughts on Machine Learning – Dealing with Skewed Classes
- Tutorial: NumPy
Aula 04 – Agrupamento (k-means); Redução de Dimensionalidade (PCA)
- Making sense of principal component analysis, eigenvectors & eigenvalues
- What is an eigenvector of a covariance matrix
- How do I calculate the covariance matrix without any built-in functions or loops in MATLAB?
- Principal Components Analysis (lecture)
- CS229: Principal components analysis
- Calculating Covariance with Python and Numpy
- Mean Vector and Covariance Matrix
- K-Means Clustering in Python
Aula 05 – Detecção de Anomalias
- Can anomaly detection work without the assumption of Normal Distribution of the underlying data?
Normal distribution – Maximum Likelihood Estimation - Anomaly detection with the normal distribution
- Transform Data to Normal Distribution
- scipy.stats.boxcox
- Como computar o determinante de uma matriz com numpy
- Power transform (Wikpedia)
- Tips for Recognizing and Transforming Non-normal Data
- Data Preparation for Predictive Modeling: Resolving Skewness
- MLE
- Prova relativa à estimação por máxima verossimilhança apresentada em aula
Aula 06 – Sistemas de Recomendação; AM & Big Data
- An Introduction to Recommendation Systems
- Gradient Descent and SGD
- A Brief (and Comprehensive) Guide to Stochastic Gradient Descent Algorithms
Aula 07 – Redes Neurais – representação
- What the Hell is Perceptron?
- Dendritic Computation (Michael London and Michael Hausser)
- An Introduction to Recommendation Systems
- Import AI
- This Emergent Mind project implements a JavaScript-based neural network with back-propagation that can learn various logical operators.
- A Gentle Introduction to Mini-Batch Gradient Descent and How to Configure Batch Size
- Wikipedia: Coordinate descent
- Implementação de uma RNA para o problema XOR
- [3Blue1Brown] Gradient descent, how neural networks learn | Deep learning, part 2
- [Khan Academy] Multivariable functions | Multivariable calculus | Khan Academy
Aula 08 – Redes Neurais – aprendizado
- Understanding Xavier Initialization In Deep Neural Networks
- SWISH: A SELF-GATED ACTIVATION FUNCTION
- A Step by Step Backpropagation Example
- Algumas soluções para cs231n
- JavaScript-based neural network with back-propagation that can learn various logical operators
- Debugging Strategies
- How to Develop a Mindset for Math
- Machine Learning – Tom Mitchell
- Yes you should understand backprop
- Improve your neural networks – Part 1 [TIPS AND TRICKS]
- 37 Reasons why your Neural Network is not working
- 8 Tactics to Combat Imbalanced Classes in Your Machine Learning Dataset
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
- My Neural Network isn’t working! What should I do? (Aug. 19, 2017)
- How to debug neural networks.
- Hung-yi Lee
- Yann LeCun – How does the brain learn so much so quickly? (CCN 2017)
- Epoch vs Batch Size vs Iterations
- Activation Functions: Neural Networks
Aula 09 – Redes Profundas; Introdução ao Keras
- DEEP LEARNING STARTUPS, USE CASES & BOOKS
- Using deep learning to forecast ocean waves
- Neural Networks Tutorial – A Pathway to Deep Learning
- Deep Learning Video Tutorials
- Jeff Dean’s Talk on Large-Scale Deep Learning: aqui e aqui.
Aula 10 – Redes de Convolução
- Understanding Convolutions
- Reference to learn how to interpret learning curves of deep convolutional neural networks
- Image Super-Resolution Using Deep Convolutional Networks
- A Beginner’s Guide to Recurrent Networks and LSTMs