GCP - Machine Learning
GCP - Machine Learning
overview
- Machine learning
- one branch of the field of artificial intelligence.
- a way of solving problems without explicitly coding the solution.
- Instead, build systems that improve themselves over time through repeated exposure to sample data, training data.
Major Google applications use machine learning like YouTube, Photos, the Google Mobile App and Google Translate.
The Google Machine Learning Platform
TensorFlow / Cloud ML
- available as a cloud service
- can add innovative capabilities to your own applications.
- an open source software library
- developed by Google Brain for Google’s internal use
- and then open source so that the world could benefit.
- open source tool to build and run neural network models
- exceptionally well suited for machine learning applications like neural networks.
- wide platform support:
- CPU or GPU; mobol, server, or cloud
- pre-trained ML models build by Google
- with pre-trained models and a platform to generate your own tailored models.
- Speech:
- stream results in real time, detects 80 languages
- Vision:
- identify objects, landmarks, text, and content
- Translate:
- language translation including detection
- Natural language:
- Structure, meaning of text
- fully modern managed machine learning services
- familiar notebook-based developer experience
- Optimized for Google infrastructure
- integrates with BigQuery and Cloud Storage
- As with other GCP products, there’s a range of services that stretches from the highly general to the pre-customized.
- can run TensorFlow wherever you like
- GCP is an ideal place
- because machine learning models need lots of on-demand compute resources and lots of training data.
- TensorFlow also take advantage of Tensor Processing Units
- hardware devices
- designed to accelerate machine learning workloads with TensorFlow.
- GCP makes them available in the cloud with Compute Engine virtual machines.
- Each cloud TPU provides up to 180 teraflops of performance.
- pay for what you use
- no upfront capital investment required.
- available as a cloud service
Google Cloud Machine Learning Engine
- managed service.
- easily build machine learning models that work on any type of data of any size.
- It can take any TensorFlow model
- and perform large-scale training on a managed cluster.
Cloud Machine Learning Platform for applications.
- Generally two categories (whether the data is structured or unstructured)
- structured data
- can use ML for various kinds of classification and regression tasks
- like customer churn analysis, product diagnostics and forecasting.
- can be the heart of a recommendation engine
- for content personalization and cross-sells and up-sells.
- can use ML to detect anomalies
- such as in fraud detection, sensor diagnostics or log metrics.
- can use ML for various kinds of classification and regression tasks
- unstructured data
- can use ML for image analytics
- such as identifying damaged shipment, identifying styles and flagging content.
- can do text analytics
- such as call center, blog analysis, language identification, topic classification and sentiment analysis.
- can use ML for image analytics
- structured data
In many innovative applications for machine learning, several applications are combined.
- one customers posted praise for one of your products on social media, your application could automatically reach out to them with a customized discount on another product they’ll probably like?
Machine learning APIs
- Google Cloud offers a range of machine learning APIs suited to specific purposes.
- encapsulates powerful machine learning models behind an easy-to-use API.
- add various machine learning capabilities to applications without worry about the details of how they are provided.
Sight
The Cloud Vision API
- enables developers to understand the content of an image.
- quickly classifies images into thousands of categories
- logo/label detection
- detects individual objects within images,
- finds and reads printed words contained within images.
- analysis images with a simple REST API
- You can
- use it to build metadata on your image catalog, moderate offensive content or even do image sentiment analysis.
- gain insight from images
- detect inappropriate content
- analyze sentiment
- extract text
The Cloud Video Intelligence API
- annotate the contents of videos
- support variety of video formats.
- detect scene changes
- flag inappropriate context
- identify key entities, nouns, within the video and when they occur.
- use it to make video content searchable and discoverable.
conversation
The Cloud Speech API
- enables developers to convert audio to text.
- The API recognizes over 80 languages and variants.
- You can
- transcribe the text of users,
- dictating in an applications’ microphone,
- enable command and control through voice or transcribe audio files.
Language
The Cloud Translation API
- provides a simple, programmatic interface for translating an arbitrary string into a supported language.
- the API can detect the source language
- translate arbitrary strings between thousands of language pairs
The Cloud Natural Language API
- offers natural language understanding technologies
- text/syntax analysis, reveal structure and meaning of text
- breaking down sentences supplied by our users into tokens,
- identify the nouns, verbs, adjectives, and other parts of speech
- and figure out the relationships among the words.
- It can extract information about items mentioned
- do entity recognition.
- parse text
- and flag mentions of people, organizations, locations, events, products, and media.
- It can understand the overall sentiment expressed in a block of text.
- return text in real time
- highly accurate,
- even in noisy environments
- access from any device
- It has these capabilities in multiple language
- including English, Spanish, and Japanese.
structured data
AutoML APIs
AI Platform
.
This post is licensed under CC BY 4.0 by the author.
Comments powered by Disqus.