Visão Geral

Curso Machine Learning Specialization, apresenta o campo emocionante e de alta demanda do aprendizado de máquina. Por meio de uma série de exercícios práticos, você ganhará experiência aplicada nas principais áreas de aprendizado de máquina, incluindo previsão, classificação, clustering, visão computacional e aprendizado profundo. Você aprenderá a analisar dados e construir aplicativos inteligentes que podem fazer previsões a partir dos dados.

Este Curso Machine Learning Specialization, construirá sua base em Python primeiro, depois seguirá pelo aprendizado de máquina clássico usando Scikit Learn, seguido pelo aprendizado profundo usando a estrutura Tensorflow 2.x.

Publico Alvo

• Analistas de dados
• Engenheiros e desenvolvedores de aprendizado de máquina
• NSF
• Estudantes em tempo integral
• Analistas de dados

Materiais

Conteúdo Programatico

Python Fundamental

Get Started on Python

1. Overview of Python
2. Set Python
3. Code Your First Python Script

Data Types

1. Number
2. String
3. List
4. Tuple
5. Dictionary
6. Set

Operators

1. Arithmetic Operators
2. Compound Operators
3. Comparison Operators
4. Membership Operators
5. Logical Operators

Control Structure, Loop and Comprehension

1. Conditional
2. Loop
3. Iterating Over Multiple Sequences
4. Comprehension

Function

1. Function Syntax
2. Return Values
3. Default Arguments
4. Variable Arguments
5. Lambda, Map, Filter

Modules & Packages

1. Import Modules and Packages
2. Python Standard Packages
3. Third Party Packages

Data Analytics and Visualization with Python

Data Preparation

1. Data Analytics with Pandas
2. Pandas DataFrame and Series
3. Import and Export Data
4. Filter and Slice Data
5. Clean Data

Data Transformation

1. Join Data
2. Transform Data
3. Aggregate Data

Data Visualization

1. Data Visualization with Matplotlib and Seaborn
2. Visualize Statistical Relationships with Scatter Plot
3. Visualize Categorical Data with Bar Plot
4. Visualize Correlation with Pair Plot and Heatmap
5. Visualize Linear Relationships with Regression

Data Analysis

1. Statistical Data Analysis
2. Time Series Analysis

Advanced Data Analytics

1. Data Piping
2. Groupby and Apply Custom Functions
3. Linear Regression

Machine Learning with Scikit Learn

Overview of Machine Learning and Scikit Learn

1. Introduction to Machine Learning
2. Supervised vs Unsupervised Learnings
3. Machine Learning Applications and Case Studies
4. What is Scikit Learn
5. Installing Scikit-Learn

Classification

1. What is Classification
2. Classification Algorithms
3. Classification Workflow
4. Confusion Matrix
5. Binary Classification Metrics
6. ROC and AUC

Regression

1. What is Regression?
2. Regression Algorithms
3. Regression Workflow
4. Regression Metrics
5. Overfitting and Regularizations

Clustering

1. What is Clustering
2. K-Means Clustering
3. Silhouette Analysis
4. Dendrogram and Hierarchical Clustering

Topic 3.5 Principal Component Analysis

1. Curse of Dimensionality Issue
2. What is Principal Component Analysis (PCA)
3. Feature Reduction with PCA

Basic Neural Network with Tensorflow

Introduction to Deep Learning

1. Machine Learning vs Deep Learning
2. Deep Learning Methodology
3. Overview of Tensorflow Keras
4. Install and Run Tensorflow Keras
5. Basic Tensorflow Keras Operations

Neural Network for Regression

1. What is Neural Network (NN)?
2. Loss Function and Optimizer
3. Build a Neural Network Model for Regression

Neural Network for Classification

1. One Hot Encoding and SoftMax
2. Cross Entropy Loss Function
3. Build a Neural Network Model for Classification

Advanced Neural Networks with Tensorflow

Convolutional Neural Network (CNN)

1. Introduction to Convolutional Neural Network?
2. ImageDataGenerator
3. Image Classification Model with CNN
4. Data Augmentation and Dropout

Transfer Learning

1. Introduction to Transfer Learning
2. Applications of Pre-Trained Models
3. Fine Tuning Pre-Trained Models

Recurrent Neural Network (RNN)

1. Introduction to Recurrent Neural Network (RNN)
2. LSTM and GRU
3. Build a RNN Model for Time Series Forecasting
4. Build a RNN Model for Sentiment Analysis