Tools for Analyzing Text.
- Amazon Comprehend
- Amazon Kendra
- Amazon Textract
What Is Amazon
Comprehend?
- Comprehend uses natural language processing (NLP) to help you understand the meaning and sentiment in your text. For example,
you can automate understanding of whether people are saying positive or
negative things about your service. - You can also pick up on key phrases.
- Comprehend is a way of automating comprehension at scale.
What Is Kendra?
Kendra allows you to create an intelligent search service powered by machine learning. Enterprise search applications can
bridge between different silos of information (such as S3 buckets, file
servers, and websites), allowing your enterprise to have all the data
intelligently in one place.
What Is Textract?
Textract uses machine learning and OCR (optical character recognition), to automatically extract text, handwriting, and data from scanned documents.
- input: jpeg, png, pdf, tiff
- output: extracted text, structure, analysis
What is Amazon Forecast?
Amazon Forecast is a time-series forecasting service that uses machine learning and is built to give you important business insights.
You can send your data to Amazon Forecast and it will automatically learn your data, select the right machine-learning algorithm, and then
help you forecast your data.
Based on historical and related data.
What Is Fraud
Detector?
An AWS AI service that is built to detect fraud in your data. Create a fraud detection machine learning model that is based on your data. You can also quickly automate this process.
Amazon Fraud Detector is a fully managed fraud detection service that automates the detection of potentially fraudulent activities online. These activities include unauthorized transactions and the creation of fake accounts or phishing. Amazon Fraud Detector works by using machine learning to analyze your data.
Which services Work with
Text and Speech?
- Amazon Transcribe
- Amazon Lex
- Amazon Polly
What Is Transcribe?
Transcribe is used to covert speech to text automatically. You can use this
service to generate subtitles on the fly.
What Is Lex?
Lex allows you to build conversational interfaces in your applications using
natural language models. Chances are that when you are talking to an
automated bot online, you are interacting with the Lex service on the
backend. (a -lex -a)
What Is Polly?
Polly turns your text into lifelike speech and allows you to create applications that talk to and interact with you using a variety of languages and accents.
What Is Amazon
Rekognition?
Rekognition is Amazon’s computer vision product that automates the recognition of pictures and videos using deep learning and neural networks. You can use these processes to understand and label what is in pictures and videos.
Automatically moderate content allowing your applications and websites to be family friendly. This is a common exam scenario.
What is Amazon SageMaker?
Amazon SageMaker is a fully managed machine learning service provided by Amazon Web Services (AWS). It is designed to make it easier for developers and data scientists to build, train, and deploy machine learning models at scale.
What are the Machine Learning Workflow Components?
- Ground Truth: Set up and manage labeling jobs for training datasets using active learning and human labeling.
- Notebook: Access a managed Jupyter Notebook environment.
- Training: Train and tune models.
- Inference: Package and deploy your machine learning models at scale.
What are the SageMaker Stages?
- Create a Model
This is the place that will provide
predictions for your endpoint. - Create an Endpoint Configuration
This is where you specify the model to use, inference instance type, instance count, variant name, and weight. This can sometimes be called a
production variant. - Create an Endpoint
This is where the model is published, and you can invoke the
model using the InvokeEndpoint() method.
What is SageMaker Neo?
Customize your machine learning models for specific CPU hardware, such as ARM, Intel, and NVIDIA processors. It includes a compiler to convert the machine learning model to an environment that is optimized to execute the model on the target architecture.
What is Elastic Inference?
Elastic Inference (EI)
EI speeds up throughput and decreases latency of realtime inferences deployed on SageMaker hosted services
using only CPU-based instances. It is much more costeffective than a full GPU instance.
It must be configured when you create a deployable
model. EI is not available for all algorithms yet.
What Is Amazon Translate?
A machine learning service that allows you to automate language translation.
Using deep learning and neural networks, Amazon Translate allows you
to translate from one language to another.
