Curso Deep Learning with Tensorflow and Python

  • DevOps | CI | CD | Kubernetes | Web3

Curso Deep Learning with Tensorflow and Python

32 horas
Visão Geral

Curso Deep Learning with Tensorflow and Python, O Tensorflow é a estrutura de machine learning/deep learning de código aberto mais popular e poderosa desenvolvida pelo Google para todos. O Tensorflow possui muitas APIs poderosas de Machine Learning, como Rede Neural, Rede Neural Convolucional (CNN), Rede Neural Recorrente (RNN), Incorporação de Palavras, Seq2Seq, Redes Gerativas Adversariais (GAN), Aprendizagem por Reforço e Meta Aprendizagem.

O Tensorflow é baseado no Python, a linguagem de programação mais popular para análise e engenharia de dados do mundo. Neste curso, você se equipará com os conhecimentos básicos e avançados de Python. Depois disso, você aprenderá os tópicos básicos e avançados do Tensorflow. Ao concluir este curso, você poderá desenvolver seu próprio modelo NN, CNN e RNN para reconhecimento de imagem e análise sentimental usando Tensorflow ou Keras.

Objetivo

Ao final do Curso Deep Learning with Tensorflow and Python, os alunos serão capazes de

  • avaliar plataformas de aprendizado profundo usando Python e Tensorflow
  • facilitar mudanças usando Python,
  • analisar as causas raiz de quaisquer problemas no Python
  • aplicar técnicas complexas e avançadas de análise e modelagem usando Python
  • desenvolver novos algoritmos usando Python
  • desenvolver modelos de regressão usando Tensorflow
  • descobrir relacionamentos subjacentes em modelos de regressão
  • desenvolver modelos de classificação usando Python e Tensorflow
  • criar modelos de aprendizado de transferência
  • desenvolver procedimentos de teste para avaliar modelos de aprendizado profundo
Publico Alvo
  • Estudantes em tempo integral
  • Analistas de dados
  • Analistas de dados
  • Engenheiros e desenvolvedores de aprendizado de máquina
Materiais
Inglês + Exercícios + Lab Pratico
Conteúdo Programatico

Get Started with Python

  1. Overview
  2. Install Python
  3. Install Sublime Text & PyCharm
  4. First Python Script
  5. Comment

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
  6. Identity Operators

Control Structure

  1. Conditional
  2. Loop
  3. Iterating Over Multiple Sequences
  4. Break & Continue
  5. Loop with Else

Function

  1. Function Syntax
  2. Return Single Value
  3. Return Multiple Values
  4. Passing Arguments
  5. Default Arguments
  6. Variable Arguments
  7. Decorator
  8. Lambda, Map, Filter

Modules & Packages

  1. Modules
  2. Packages
  3. Python Standard Libraries
  4. Install Third Party Packages
  5. Anaconda Packages

Advanced Python

Comprehensions & Generators

  1. Comprehension Syntax
  2. Types of Comprehension
  3. Generator Syntax
  4. Types of Generators

File and Directory Handling

  1. Read and Write Data to Files
  2. Manage File and Folders with Python OS Module
  3. Manage Paths with Python Pathlib Module

Object Oriented Programming

  1. Introduction to Object Oriented Programming
  2. Create Class and Objects
  3. Method and Overloading
  4. Initializer & Destructor
  5. Inheritance
  6. Polymorphism

Database

  1. Setup SQLite3 database
  2. Apply CRUD operations on SQLite3
  3. Integrate to external databases

Error Handling Using Exception

  1. Exceptions versus Syntax Errors
  2. Handle Exceptions with Try and Except blocks
  3. The Else clause
  4. Clean up with Finally

Intro to Useful Packages

  1. Numpy
  2. Matplotlib
  3. Pandas

Python Assessment

Basic Tensorflow

Overview of Machine Learning & Tensorflow

  1. Overview of Machine Learning and Deep Learning
  2. Introduction to Tensorflow 2.x
  3. Install Tensorflow 2.x

Basic Tensorflow Operations

  1. Basic Tensor Data Types
  2. Constant, Variable & Gradient
  3. Matrix Operations
  4. Eagle Mode vs Graph Mode

Datasets

  1. MNIST Handwritten Digits and Fashion Datasets
  2. CIFAR Image Dataset
  3. IMDB Text Dataset

Neural Network for Regression

  1. Introduction to Neural Network (NN)
  2. Activation Function
  3. Loss Function and Optimizer
  4. Machine Learning Methodology
  5. Build a NN Predictive Regression Model
  6. Load and Save Model

Neural Network for Classification

  1. Softmax
  2. Cross Entropy Loss Function
  3. Build a NN Classification Model

Advanced Tensorflow

Convolutional Neural Network (CNN)

  1. Introduction to Convolutional Neural Network (CNN)
  2. Convolution & Pooling
  3. Build a CNN Model for Image Recognition
  4. Overfitting and Underfitting Issues
  5. Methods to Solve Overfitting
  6. Small Dataset Overfitting Issue
  7. Data Augmentation & Dropout

Transfer Learning 

  1. Introduction to Transfer Learning
  2. Pre-trained Models
  3. Transfer Learning for Feature Extraction & Fine Tuning

Recurrent Neural Network (RNN)

  1. Introduction to Recurrent Neural Network (RNN)
  2. Types of RNN Architectures
  3. LSTM and GRU
  4. Word Embedding
  5. Build a RNN Model for Sentiment Analysis
  6. Build a RNN Model for Time Series Prediction
TENHO INTERESSE

Cursos Relacionados

Curso Ansible Red Hat Basics Automation Technical Foundation

16 horas

Curso Terraform Deploying to Oracle Cloud Infrastructure

24 Horas

Curso Ansible Linux Automation with Ansible

24 horas

Ansible Overview of Ansible architecture

16h

Advanced Automation: Ansible Best Practices

32h

Curso Red Hat DevOps Pipelines and Processes: CI/CD with Jenkins

24h

Curso Cloud Security and DevSecOps Automation

32 horas