Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of data science problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way that supports experimentation. Course Objectives: Identify why deep learning is currently popular Optimize and evaluate models using loss functions and performance metrics Mitigate common problems that arise in machine learning Create repeatable and scalable training, evaluation, and test datasets
Este curso faz parte do Programa de cursos integrados Machine Learning with TensorFlow on Google Cloud Platform
Launching into Machine Learning
oferecido por
Informações sobre o curso
37,602 visualizações recentes
Habilidades que você terá
TensorflowBigqueryMachine LearningData Cleansing
Programa - O que você aprenderá com este curso
Semana
19 minutos para concluir
Introduction
In this course you’ll get foundational ML knowledge so that you understand the terminology that we use throughout the specialization. You will also learn practical tips and pitfalls from ML practitioners here at Google and walk away with the code and the knowledge to bootstrap your own ML models.
2 vídeos ((Total 9 mín.))
1 hora para concluir
Practical ML
In this module, we will introduce some of the main types of machine learning and review the history of ML leading up to the state of the art so that you can accelerate your growth as an ML practitioner.
10 vídeos ((Total 62 mín.)), 1 teste
10 videos
Introduction1min
Supervised Learning5min
Regression and Classification11min
Short History of ML: Linear Regression7min
Short History of ML: Perceptron5min
Short History of ML: Neural Networks7min
Short History of ML: Decision Trees5min
Short History of ML: Kernel Methods4min
Short History of ML: Random Forests4min
Short History of ML: Modern Neural Networks8min
1 exercício prático
Module Quiz6min
1 hora para concluir
Optimization
In this module we will walk you through how to optimize your ML models.
13 vídeos ((Total 60 mín.)), 1 teste
13 videos
Introduction42s
Defining ML Models4min
Introducing the Natality Dataset6min
Introducing Loss Functions6min
Gradient Descent5min
Troubleshooting a Loss Curve2min
ML Model Pitfalls6min
Lab: Introducing the TensorFlow Playground6min
Lab: TensorFlow Playground - Advanced3min
Lab: Practicing with Neural Networks6min
Loss Curve Troubleshooting1min
Performance Metrics3min
Confusion Matrix5min
1 exercício prático
Module Quiz6min
3 horas para concluir
Generalization and Sampling
Now it’s time to answer a rather weird question: when is the most accurate ML model not the right one to pick? As we hinted at in the last module on Optimization -- simply because a model has a loss metric of 0 for your training dataset does not mean it will perform well on new data in the real world.
9 vídeos ((Total 64 mín.)), 3 testes
9 videos
Introduction1min
Generalization and ML Models6min
When to Stop Model Training5min
Creating Repeatable Samples in BigQuery6min
Demo: Splitting Datasets in BigQuery8min
Lab Introduction1min
Lab Solution Walkthrough9min
Lab Introduction2min
Lab Solution Walkthrough23min
1 exercício prático
Module Quiz12min
50%
comecei uma nova carreira após concluir estes cursos
44%
consegui um benefício significativo de carreira com este curso
20%
recebi um aumento ou promoção
Melhores avaliações
This is an awesome module. It will open up so much inside story of ML process which is core of the topic with such a simplicity. It greatly increases my interest into this topic and this course :)
Good course, covering all the basics about machine learning and most importantly, everything that surrounds an ml project and you need to take into account to make your ml project successful.
Sobre Google Cloud
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Sobre o Programa de cursos integrados Machine Learning with TensorFlow on Google Cloud Platform
What is machine learning, and what kinds of problems can it solve? What are the five phases of converting a candidate use case to be driven by machine learning, and why is it important that the phases not be skipped? Why are neural networks so popular now? How can you set up a supervised learning problem and find a good, generalizable solution using gradient descent and a thoughtful way of creating datasets? Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models. and offer high-performance predictions. Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem. Finally, learn how to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. You will experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform.
> By enrolling in this specialization you agree to the Qwiklabs Terms of Service as set out in the FAQ and located at: https://qwiklabs.com/terms_of_service <
Perguntas Frequentes – FAQ
Posso assistir uma prévia do curso antes de me inscrever?
Sim, você pode assistir uma prévia do primeiro vídeo e ver programa do curso antes de se inscrever. Você precisa comprar o curso para ter acesso ao conteúdo não incluído na prévia.
Quando terei acesso às palestras e às tarefas?
Se decidir se inscrever no curso antes da data de início da sessão, terá acesso a todos os vídeos das palestras e leituras do curso. Também poderá enviar tarefas assim que a sessão começar.
O que recebo ao me inscrever?
Uma vez inscrito, e tão logo sua sessão tenha iniciado, você terá acesso a todos os vídeos e outros recursos, incluindo itens de leitura e fórum de discussão do curso. Você poderá ver e enviar tarefas práticas e concluir tarefas com nota atribuída obrigatórias para obter uma nota e um Certificado de Curso.
Quando receberei meu Certificado de Curso?
Se você concluir o curso com êxito, seu Certificado de Curso eletrônico será adicionado à sua página de Participações e você poderá imprimi-lo ou adicioná-lo ao seu perfil no LinkedIn.
Por que não posso assistir este curso como ouvinte?
Este curso é um dos poucos oferecidos pela Coursera que está disponível apenas para alunos que tenham pago ou recebido auxílio financeiro, quando disponível.
Qual é a política de reembolso?
Existe algum auxílio financeiro disponível?
Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.
O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.
© 2019 Coursera Inc. Todos os direitos reservados.
