Machine Learning with AWS

Build a simple web app using Flask to process text with natural language processing, translate text to languages, and analyze sentiment and parts of speech using AWS machine learning services.

Build a Flask-backed backend for an ML app, collecting user input and language, and integrating NLP features like spam detection, sentiment analysis, POS tagging, NER, and translation for chatbots.

Develop a Python translate function using an SDK to convert English input into a user-selected language, returning the result as JSON and integrating translated text into the application.

Explore building a web app that uses AWS Translate to translate input text into a language by calling a translation function with text and language code, and add languages.

Build a sentiment analysis function using AWS Comprehend to extract positive, negative, and neutral scores from text, and apply insights to product reviews and marketing strategies.

Explore building a sentiment analysis app with Amazon Comprehend, classify text into positive, neutral, and negative, and map sentiments to scores while customizing the ML model.

Learn part-of-speech tagging and named entity recognition in Python, produce JSON, explore word sense disambiguation and sentiment analysis, and build NLP apps with Flask or Bottle for chat box agents.

Learn to recognize named entities in text with the detect entities function, identifying person, location, organization, and time, then extract results into a JSON-friendly dictionary for a web app.

Explore Amazon Comprehend, a natural language processing service using machine learning to extract key phrases, sentiment, syntax, topics, and entities like people, brands, and locations, enabling semantic search and personalization.

Explore Amazon Comprehend, a natural language processing tool that extracts entities, key phrases, language, sentiment, and parts of speech from text, with analyzable results.

Explore how to use Python boto3 to run Amazon Comprehend for language detection and text extraction, manage permissions and IAM policies, and apply Comprehend to images.

Learn how to use Amazon Comprehend with Python boto3 to detect key phrases in text by running a script.

Use Python boto3 to work with comprehend and extract key phrases, sentiment, and syntax from text. Explore how comprehend reveals pronouns and sentence structure in sample text.

Discover how Amazon Lex combines automatic speech recognition and natural language understanding to build engaging voice and text chatbots, with easy deployment, cost efficiency, and real-world use cases.

Explore how to design an Amazon Lex v2 bot by defining intents, slots, and utterances, configuring dialogue prompts, and implementing Lambda fulfillment to deploy across messaging platforms.

Explore how Amazon Polly converts text into natural speech with dozens of voices across languages, allowing pronunciation, volume, and speed controls for engaging e-learning and telephony applications.

Build a functional chatbot with Amazon Lex by defining intents, slots, and prompts, configuring responses, testing, and publishing to multiple messaging platforms.

Explore Amazon Polly's text-to-speech capabilities, customize pronunciation with lexicons, and experiment with languages, voices, pitch, and emphasis to synthesize speech.

Create a Python script with boto3 to synthesize speech using AWS Polly, install boto3, set permissions, choose a voice, and run the script to generate audio from text.

Explore Amazon Rekognition on AWS, mastering object detection, image and video analysis, text in images, image moderation, and face comparison to build scalable, integrated applications.

Explore object and scene detection with AWS, learning how labels like person, water, beach identify entities and how confidence scores express prediction certainty for surveillance and inspection.

Explore object and scene detection using practical examples, identifying entities like person, skateboard, car, building, and scenes such as parking lots and urban streets.

Use Python boto3 to analyze an image, detect labels and extract text, aiding occupancy detection with labels and confidence scores.

Detect and analyze faces in images by producing bounding boxes, extracting attributes such as gender, eyeglasses, eye and nose landmarks, and pose angles, plus quality metrics for brightness and sharpness.

Explore practical facial analysis with AWS in machine learning by detecting multiple faces, facial landmarks, and attributes such as age range, smiling, sunglasses, eye openness, and gender, with bounding boxes.

Discover how to detect faces in images and analyze facial landmarks using Python boto3 in AWS machine learning workflows, building practical face recognition capabilities.

Explore celebrity recognition, a deep learning based detection and identification feature that indexes digital image libraries by celebrity, updating daily with new personalities, and offering opt-out privacy options.

Practice celebrity recognition with an image-based demonstration, including uploading or dragging and dropping a local image to test recognition.

Develop a celebrity recognition workflow by comparing celebrities in images with a Python script, processing photos and presenting information about identified figures.

Demonstrates face comparison by uploading a source and a target image, detecting faces, and returning a similarity percentage and bounding boxes to identify a person in a group.

Practice practical face comparison by comparing a source image to a target image, obtaining similarity scores, and examining landmark features like eyes, nose, and mouth, with upload or drag-and-drop options.

Learn to perform face comparison with Python boto3 on AWS, interpret confidence scores, and compare source and target images including background contexts.

Explore text in image detection that outputs text labels with bounding boxes and confidence, designed for real world images, enabling text metadata, license plate recognition, and media applications.

demonstrates using aws text in image to detect and extract text from images, with live examples like a shirt image and a license plate, highlighting english only support.

Learn how to detect text in images using Python with boto3 and an AWS service, extracting lines of text, their positions, and confidence scores.

Explore visual analysis in machine learning with AWS by uploading videos to analyze objects, people, celebrities, and landmarks, with outputs such as detected faces and recognized celebrities or landmarks.

Amazon Transcribe uses deep learning to convert audio to text, analyze audio files, and generate transcripts with timestamps.

Discover Amazon Translate, a deep learning powered, fast and affordable AWS machine translation service that localizes websites and apps across many languages for multilingual insights and accessible content.

Watch a practical demonstration of Amazon Transcribe, creating a transcription job from uploaded audio or video, selecting English, enabling speaker identification, and downloading the resulting transcript.

Learn how to use a python script to create and monitor a transcription job, wait for completion, and obtain the full transcription of an audio file.

Learn how to use Amazon Translate in AWS to auto-detect the source language and translate text into multiple targets, including Arabic, Chinese, and German.

Explore translating text with a translation service using Python boto3, converting between English and German by specifying source and target language codes, and validating results from a command prompt.

discover Amazon SageMaker, a fully managed platform that simplifies training, deploying, and testing machine learning models, while optimizing performance and scaling across resources.

Explore AWS DeepLens, a voice-first video camera that runs machine learning models on-device using MXNet and Python, with six sample projects including face and activity detection.

Prepare your data for machine learning by uploading historical customer data to a bucket, organizing files, and setting up data for model training and prediction.

Create a training datasource in the aws machine-learning console by specifying the input data location and selecting a schema with binary, numeric, and target attributes.

Learn how to create an ml model and explore various models through the creation process.

Explore generating real-time predictions for single observations and batch predictions for groups from a machine learning model, using prepared data to evaluate outcomes and guide model evolution.

Learn to clean and manage your machine learning workflow on AWS by extracting data, evaluating predictions, and deleting temporary files to keep your bucket organized.