Visão Geral

O Curso Machine Learning in TensorFlow Keras Fundamentals, foi desenvolvido para usuários que desejam mergulhar nos domínios da Inteligência Artificial. Naturalmente vem como um seguidor do curso Ciência de Dados Básica em Python.

Materiais

Conteúdo Programatico

Introduction

1. What is ML?
2. Where can I find it in real life?
3. Why now?
4. What are the three main categories of ML?
5. Supervised learning
6. Unsupervised learning
7. Reinforcement learning (demo)
8. ML pipeline

Machine Learning with sci-kit

1. ML pipeline review
2. Scikit Python Library
3. Data representation
4. Feature matrix
5. Target array
6. Iris dataset example
7. Estimator API
8. Linear Regression
9. Simple Linear Regression
10. Model Evaluation
11. Polynomial Regression
12. Selecting the best model
13. The bias-variance trade-off
14. Logistic Regression
15. Who survives the Titanic?
16. Naive Bayes
17. Gaussian Naive Bayes
18. Multinomial Naive Bayes
19. Categorical Naive Bayes
20. k Nearest Neighbours
21. k-Means Clustering
22. Dimensionality reduction
23. Principal Components Analysis (PCA)
24. Singular Value Decomposition (SVD)
25. Decision Trees
26. Random Forests

Hands-on Lab:

• Playing around with different values affecting the bias and the variance, calculating precision, recall, F1 and F2-scores, comparing different models on the training and testing accuracies
• Doing a little bit of data preprocessing, analyzing the difference between categorical and numerical data, plotting some relevant statistical values and visually inspecting the correlation between features

Neural Networks in Tensorflow/Keras

1. Artificial Neural Networks (ANNs)
2. Neurons
3. Layers
4. Activation Functions
5. More vocabulary
6. Popular Frameworks
7. Keras
8. Linear Regression
9. Defining Models in Keras
10. Training and predicting
11. Fashion MNIST example

Hands-on Lab:

1. Creating our first custom neural network model
2. Choosing the number of layers and the number of neurons per layer
3. Tweaking the learning rate
4. Training the neural network on real world data

Convolutional Neural Networks (peek)

1. Motivation behind CNNs
2. CNN Building blocks
3. Convolution Layers
4. Pooling Layers
5. CNNs in Keras
6. Data Augmentation
7. Architectures

NLP using Deep Learning

1. Spam detector
2. Sentiment analyzer
3. Autocomplete

Module 6: Reinforcement Learning

1. Frozen Lake demo
2. Flappy Bird demo

Recommender Systems

1. Data preparation
2. Cosine distance
3. SVD for recommender systems
4. Autoencoder demo