Machine Learning with TensorFlow on Google Cloud Platform Specialization

Start Date: 07/12/2020

Course Type: Specialization Course

Course Link:

Explore 1600+ online courses from top universities. Join Coursera today to learn data science, programming, business strategy, and more.

About Course

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: <

Course Syllabus

How Google does Machine Learning
Launching into Machine Learning
Intro to TensorFlow
Feature Engineering

Deep Learning Specialization on Coursera

Course Introduction

Learn ML with Google Cloud. Real-world experimentation with end-to-end ML. Machine Learning with TensorFlow on Google Cloud Platform Specialization This 1-week, accelerated online course gives you an in depth overview of machine learning with TensorFlow on Google Cloud Platform. We'll learn everything from how to implement a naive classifier to how to use Naive Bayes to estimate classification rates. We'll also cover basic machine learning techniques including how data are preprocessed and merged to minimize overfitting. We'll also cover recognizing errors in data and how to correct for those errors using optimizers. You'll even finish the course with a series of hands-on labs with networked play-it-safe practices to give you a base to work with on your personal machine learning pipeline. By the end of this course, you'll be able to: - Prove your model of a machine learning problem using TensorFlow training/test examples - Solve a problem of a machine learning problem using TensorFlow evaluation of the problem - Generate an ML model from a training dataset - Scale a problem of a machine learning problem The course assumes prior knowledge of machine learning. You should have some familiarity with machine learning as well as some programming experience. The course is intended to give you a deep, intermediate understanding of how machine learning works, but it does not cover everything all machine learning algorithms. To get the most out of this course, we recommend that you take a look at the Machine Learning Specialization, which is designed to go deep into the nitty gritty of machine learning. The Special

Course Tag

Tensorflow Machine Learning Feature Engineering Cloud Computing

Related Wiki Topic

Article Example
TensorFlow TensorFlow is Google Brain's second generation machine learning system, released as open source software on November 9, 2015. While the reference implementation runs on single devices, TensorFlow can run on multiple CPUs and GPUs (with optional CUDA extensions for general-purpose computing on graphics processing units). TensorFlow is available on 64-bit Linux, macOS, and mobile computing platforms including Android and iOS.
Google Cloud Platform Google Cloud Platform is a cloud computing service by Google that offers hosting on the same supporting infrastructure that Google uses internally for end-user products like Google Search and YouTube. Cloud Platform provides developer products to build a range of programs from simple websites to complex applications.
TensorFlow TensorFlow is an open source software library for machine learning across a range of tasks, and developed by Google to meet their needs for systems capable of building and training neural networks to detect and decipher patterns and correlations, analogous to the learning and reasoning which humans use. It is currently used for both research and production at Google products,   often replacing the role of its closed-source predecessor, DistBelief. TensorFlow was originally developed by the Google Brain team for internal Google use before being released under the Apache 2.0 open source license on November 9, 2015.
Google Cloud Platform Google Cloud Platform is a part of a suite of enterprise services from Google Cloud and provides a set of modular cloud-based services with a host of development tools. For example, hosting and computing, cloud storage, data storage, translations APIs and prediction APIs.
Google Cloud Dataproc Google Cloud Dataproc (Cloud Dataproc) is a cloud-based managed Spark and Hadoop service offered on Google Cloud Platform. Cloud Dataproc utilizes many Google Cloud Platform technologies such as Google Compute Engine and Google Cloud Storage to offer fully managed clusters running popular data processing frameworks such as Apache Hadoop and Apache Spark.
Google Cloud Datastore Google Cloud Datastore (Cloud Datastore) is a highly scalable, fully managed NoSQL database service offered by Google on the Google Cloud Platform. Cloud Datastore is built upon Google's Bigtable and Megastore technology.
TensorFlow In May 2016 Google announced its tensor processing unit (TPU), a custom ASIC built specifically for machine learning and tailored for TensorFlow. The TPU is a programmable AI accelerator designed to provide high throughput of low-precision arithmetic (e.g., 8-bit), and oriented toward using or running models rather than training them. Google announced they had been running TPUs inside their data centers for more than a year, and have found them to deliver an order of magnitude better-optimized performance per watt for machine learning.
TensorFlow TensorFlow computations are expressed as stateful dataflow graphs. The name TensorFlow derives from the operations which such neural networks perform on multidimensional data arrays. These multidimensional arrays are referred to as "tensors". In June 2016, Google's Jeff Dean stated that 1,500 repositories on GitHub mentioned TensorFlow, of which only 5 were from Google.
Google Cloud Print On July 23, 2013 Google updated the service to allow printing from any Windows application, if Google Cloud Printer is installed on the machine. Another new feature is Google Cloud Print Service, which can run as a Windows service so administrators can connect legacy printers to Google Cloud Print in their businesses.
TensorFlow Starting in 2011, Google Brain built DistBelief as a proprietary, machine learning system, based on deep learning neural networks. Its use grew rapidly across diverse Alphabet companies in both research and commercial applications.
SAP Cloud Platform Initially unveiled as SAP NetWeaver Cloud belonging to the SAP HANA Cloud portfolio on October 16, 2012 the cloud platform was reintroduced with the new name SAP HANA Cloud Platform on May 13, 2013 as the foundation for SAP cloud products, including the SAP BusinessObjects Cloud. Adoption of the SAP HANA Cloud Platform has increased steadily since the platform's launch in 2012, with SAP claiming over 4000 customers and 500 partners adopting the SAP HANA Cloud Platform.
TensorFlow Among the applications for which TensorFlow is the foundation, are automated image captioning software, such as DeepDream. Google officially implemented RankBrain on 26 October 2015, backed by TensorFlow. RankBrain now handles a substantial number of search queries, replacing and supplementing traditional static algorithm based search results.
Google Cloud Print Google Cloud Print is a Google service that was created to allow any Cloud-Print-aware application (web, desktop, mobile) on any device in the network cloud to print to any printer – without Google having to create and maintain printing subsystems for all the hardware combinations of client devices and printers, and without the users having to install device drivers to the client, but with documents being fully transmitted to Google. Since July 23, 2013 it also allows printing from any Windows application, if Google Cloud Printer is installed on the machine.
Google Cloud Dataproc Cloud Dataproc includes many open source packages used for data processing, including items from the Spark and Hadoop ecosystem, and open source tools to connect these frameworks with other Google Cloud Platform products.
SAP Cloud Platform On February 27, 2017 SAP HANA Cloud Platform was renamed SAP Cloud Platform at the Mobile World Congress.
Machine learning Machine Learning poses a host of ethical questions. Systems which are trained on datasets collected with biases may exhibit these biases upon use, thus digitizing cultural prejudices. Responsible collection of data thus is a critical part of machine learning.
Active learning (machine learning) Recent developments are dedicated to hybrid active learning and active learning in a single-pass (on-line) context, combining concepts from the field of Machine Learning (e.g., conflict and ignorance) with adaptive, incremental learning policies in the field of Online machine learning.
Google Cloud Dataproc Cloud Dataproc is a Platform as a service (PaaS) product designed to combine the Spark and Hadoop frameworks with many common cloud computing patterns. Cloud Dataproc separate compute and storage, which is a relatively common design for many cloud Hadoop offerings. Cloud Dataproc utilizes Google Compute Engine virtual machines for compute and Google Cloud Storage for file storage. Cloud Dataproc has a set of control and integration mechanisms that coordinate the lifecycle, management, and coordination of clusters. Cloud Dataproc is integrated with the YARN application manager to make managing and using clusters easier.
International Conference on Machine Learning The conference attracts leading innovations in the field of machine learning. ICML is a top tier conference, and is one of the two most influential conferences in Machine Learning (along with Conference on Neural Information Processing Systems).
International Conference on Machine Learning The International Conference on Machine Learning (ICML) is the leading international academic conference in machine learning, attracting annually more than 2000 participants from all over the world. It is supported by the International Machine Learning Society (IMLS).