AWS Machine Learning

OCTOBER 19, 2023

Content moderation in Amazon Rekognition Amazon Rekognition is a managed artificial intelligence (AI) service that offers pre-trained and customizable computer vision capabilities to extract information and insights from images and videos. Import images from an Amazon Simple Storage Service (Amazon S3) bucket and provide labels.

Training 106

Training Data Social Media Ecommerce 106

AWS Machine Learning

DECEMBER 14, 2023

Amazon Comprehend is a natural-language processing (NLP) service that provides pre-trained and custom APIs to derive insights from textual data. To train a custom model, you first prepare training data by manually annotating entities in documents. The full code is available on the GitHub repo.

Banking 90

Banking Effort Score Training Tools 90

TechSee

MARCH 16, 2023

As the leader in computer vision solutions for the service industry, we at TechSee work with large organizations to help them utilize AI to automate service for their products. VI Studio uses a sampling of images labeled and tagged by humans to train computer vision AI models.

Analysis 109

Analysis Video Training Examples 109

Retently

MARCH 2, 2023

A 5-star survey is a customer feedback questionnaire that uses a 5-point rating scale to assess satisfaction with a product or service. The concept is simple: customers are asked to rate a product, service, or experience on a scale of 1 to 5 stars. How was the customer service you received? When to trigger 5-star surveys?

Survey 158

Survey Effort Score Ecommerce Customer Satisfaction 158

AWS Machine Learning

MAY 5, 2023

Amazon Kendra is an intelligent search service powered by ML, and Amazon Rekognition is an ML service that can identify objects, people, text, scenes, and activities from images or videos. However, generic search queries would span a wide range of services and across different content creation dates.

Training 101

Training Examples How To Data 101

AWS Machine Learning

MARCH 28, 2024

For example, the training data used for BloombergGPT is 51% domain-specific documents, including financial news, filings, and other financial materials. Collecting and preparing finance data Domain continual pre-training necessities a large-scale, high-quality, domain-specific dataset.

Financial 94

Financial Training Metrics Analysis 94

NobelBiz

FEBRUARY 20, 2024

Contact centers are the heartbeats of customer service, enabling seamless communication between businesses and their clientele across the globe. Play Video Table of Contents The Pitfalls of Conventional Voice Services For most clients, the difference between voice services is undetectable until significant issues arise.

Contact Center 105

Contact Center Call Center Self Service System 105

AWS Machine Learning

MARCH 22, 2023

With Amazon Rekognition Custom Labels , you can have Amazon Rekognition train a custom model for object detection or image classification specific to your business needs. Developing a Rekognition Custom Labels model to analyze images is a significant undertaking that requires time, expertise, and resources, often taking months to complete.

Training 80

Training Metrics Social Media Customers 80

AWS Machine Learning

NOVEMBER 6, 2023

Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents. Custom Queries provides a way for you to customize the Queries feature for your business-specific, non-standard documents such as auto lending contracts, checks, and pay statements, in a self-service way.

Self Service 99

Self Service Banking Training Customers 99

AWS Machine Learning

SEPTEMBER 1, 2023

Specifically, we briefly introduce MLOps principles and focus on the main differentiators compared to FMOps and LLMOps regarding processes, people, model selection and evaluation, data privacy, and model deployment. These data owners are focused on providing access to their data to multiple business units or teams.

Training 101

Training Effort Score Examples Data 101

AWS Machine Learning

FEBRUARY 24, 2023

For more information, refer to Preview: Use Amazon SageMaker to Build, Train, and Deploy ML Models Using Geospatial Data. Often these agencies are dealing with disaster imagery from low altitude and satellite sources, and this data is often unlabeled and difficult to use.

Effort Score 85

Effort Score Data Training Video 85

AWS Machine Learning

SEPTEMBER 23, 2022

In this post, we demonstrate a solution using Amazon Rekognition Custom Labels along with motion sensor camera traps to automate this process to recognize engendered species and study them. Amazon CloudWatch – A monitoring and observability service that collects monitoring and operational data in the form of logs, metrics, and events.

Training 85

Training Policies Data System 85

AWS Machine Learning

MAY 5, 2023

To create this app, they need a high-quality dataset containing clothing images, labeled with different categories. In this post, we show how to repurpose an existing dataset via data cleaning, preprocessing, and pre-labeling with a zero-shot classification model in FiftyOne , and adjusting these labels with Amazon SageMaker Ground Truth.

Fashion 75

Fashion Training Data Examples 75

AWS Machine Learning

OCTOBER 4, 2022

Unlike traditional rule-based methods, ML automatically infers patterns from data so as to perform your task of interest. Although this bypasses the need to curate rules for automation, it also means that ML models can only be as good as the data on which they’re trained. However, data creation is often a challenging task.

Data 77

Data Guidelines Video Training 77

AWS Machine Learning

APRIL 17, 2023

Furthermore, humans are also error-prone and have limited capacity to process large amounts of data, making manual efforts to detect fraud time-consuming, which can result in missed fraudulent transactions, increased losses, and reputational damage. Moreover, Amazon Fraud Detector performs label assignments and sampling for unlabeled events.

Training 71

Training Financial System Government 71

AWS Machine Learning

FEBRUARY 23, 2023

These systems require petabytes of data and thousands of compute units (vCPUs and GPUs) to train. End-to-end training – This approach involves training a DNN model that takes raw sensor data as input and outputs the driving command. However, annotations are cheap because the system learns from the data collected through human behavior.

System 89

System Automotive Training Video 89

TechSee

MARCH 2, 2023

With new AI capabilities and compelling use cases being demonstrated daily, the service industry looks forward to a new generation of AI providers that answer their needs for high-quality service automation. What resources should I allocate to bring your AI solution into my service organization?

Self Service 109

Self Service Roadmap Resources Meeting 109

AWS Machine Learning

DECEMBER 22, 2022

Launched at AWS re:Invent 2021, Amazon SageMaker Ground Truth Plus helps you create high-quality training datasets by removing the undifferentiated heavy lifting associated with building data labeling applications and managing the labeling workforce. Separately, all the projects used the same IAM role for accessing data.

Data 73

Data Policies Groups Training 73

AWS Machine Learning

NOVEMBER 16, 2022

According to an article by Cybersecurity Ventures, the damage caused by Ransomware (a type of malware that can block users from accessing their data unless they pay a ransom) increased by 57 times in 2021 as compared to 2015. In this post, we showcase how to perform Image-based Malware detection with Amazon Rekognition Custom Labels.

Training 77

Training Effort Score Metrics Resources 77

AWS Machine Learning

JULY 11, 2022

LiDAR delivers precise 3D data about its environment in real time to provide “vision” for autonomous solutions. Like any other supervised machine learning (ML) system, the point cloud data generated by LiDAR sensors should be labeled correctly in order for the ML model to make correct inferences. Solution overview.

Resources 83

Resources System Software Data 83

AWS Machine Learning

OCTOBER 5, 2022

In this post, we discuss the key elements needed to evaluate the performance aspect of a content moderation service in terms of various accuracy metrics, and a provide an example using Amazon Rekognition Content Moderation API’s. When evaluating a content moderation service, we recommend the following steps. What to evaluate.

Metrics 74

Metrics Video Guidelines Comparison 74

AWS Machine Learning

MARCH 13, 2023

Amazon SageMaker Ground Truth Plus is a managed data labeling service that makes it easy to label data for machine learning (ML) applications. One common use case is semantic segmentation, which is a computer vision ML technique that involves assigning class labels to individual pixels in an image.

Metrics 68

Metrics Tools System Data 68

AWS Machine Learning

SEPTEMBER 22, 2023

To improve the base model’s instruction-following ability, human data annotators are tasked with authoring responses to various prompts. The collected responses (often referred to as demonstration data) are used in a process called supervised fine-tuning (SFT). This occurs because the model is trained to predict the next token.

Training 95

Training Policies e-support Data 95

AWS Machine Learning

JULY 19, 2022

In this post, we discuss how you can identify solar panels on rooftops from satellite imagery using Amazon Rekognition Custom Labels. But the reality is that you need to build your own data science teams that have the specific expertise and experience to build a production machine learning (ML) application for your specific use case.

Training 70

Training Metrics Customers Data 70

AWS Machine Learning

MARCH 26, 2024

On a high level, the accounts payable process includes receiving and scanning invoices, extraction of the relevant data from scanned invoices, validation, approval, and archival. The labels are imperfect and inconsistent. In this post, we show how to automate the accounts payable process using Amazon Textract for data extraction.

Analytics 88

Analytics Financial Multi-Channel Resources 88

AWS Machine Learning

AUGUST 3, 2023

Amazon Rekognition is a fully managed service that can perform CV tasks like object detection, video segment detection, content moderation, and more to extract insights from data without the need of any prior ML experience. In some cases, a more custom solution might be needed along with the service to solve a very specific problem.

Training 63

Training Data Examples Sports 63

AWS Machine Learning

FEBRUARY 6, 2024

Traditional manual processing of adverse events is made challenging by the increasing amount of health data and costs. In this solution, we fine-tune a variety of models on Hugging Face that were pre-trained on medical data and use the BioBERT model, which was pre-trained on the Pubmed dataset and performs the best out of those tried.

Healthcare 96

Healthcare Training Data Consulting 96

AWS Machine Learning

AUGUST 10, 2022

Amazon Rekognition Custom Labels is a fully managed computer vision service that allows developers to build custom models to classify and identify objects in images that are specific and unique to your business. Rekognition Custom Labels doesn’t require you to have any prior computer vision expertise. Solution overview.

Measurement 77

Measurement Training Customers Data 77

AWS Machine Learning

JUNE 28, 2022

In computer vision, semantic segmentation is the task of classifying every pixel in an image with a class from a known set of labels such that pixels with the same label share certain characteristics. For example, the following images show a segmentation mask of the cat label. Semantic segmentation data labeling.

Training 78

Training Data Automotive Examples 78

AWS Machine Learning

NOVEMBER 23, 2022

In this post, we present an AWS architecture that processes live electrocardiogram (ECG) feeds from common wearable devices, analyzes the data, provides near-real-time information via a web dashboard. The architecture is divided in six different layers: Data ingestion. ECG data processing. Data ingestion.

Technology 72

Technology Data Healthcare Training 72

AWS Machine Learning

SEPTEMBER 9, 2022

In this post, we discuss best practices to improve the performance of your computer vision models using Amazon Rekognition Custom Labels. Rekognition Custom Labels is a fully managed service to build custom computer vision models for image classification and object detection use cases. Sample data size. Color contrast.

Tips 74

Tips Effort Score Training Metrics 74

AWS Machine Learning

SEPTEMBER 1, 2022

Bias detection in data and model outcomes is a fundamental requirement for building responsible artificial intelligence (AI) and machine learning (ML) models. For instance, an imbalanced sampling of the training data may result in a model that is less accurate for certain subsets of the data. Introduction to SageMaker Clarify.

Metrics 83

Metrics Measurement Training Groups 83

AWS Machine Learning

NOVEMBER 10, 2022

Prodege is a data-driven marketing and consumer insights platform comprised of consumer brands—Swagbucks, MyPoints, Tada, ySense, InboxDollars, InboxPounds, DailyRewards, PollFish, and Upromise—along with a complementary suite of business solutions for marketers and researchers. Overview of solution: Rekognition Custom Labels.

Training 68

Training Customer Satisfaction Innovation Consumers 68

Comm100

SEPTEMBER 23, 2021

As there continues to be an explosion of available digital services, your company must understand the need to have a complete picture of the buyer’s journey. By building proactive and unified communication and service channels, you will effortlessly deliver differentiated customer experiences that drive loyalty and sales.

Omni-Channel 198

Omni-Channel Customer Service Chatbots Customers 198

Comm100

NOVEMBER 15, 2022

As customer service operations continue to digitalize, CCaaS providers are quickly recognizing that a telephone-only offering is restricting customer base and growth. Each product can also be white-labelled to create brand consistency and increase stickiness with customers. Next steps.

Omni-Channel 186

Omni-Channel Chatbots Social Media Communication 186

AWS Machine Learning

DECEMBER 12, 2022

Amazon Lookout for Vision provides a machine learning (ML)-based anomaly detection service to identify normal images (i.e., Section 6 demonstrates how the Lookout for Vision model trained on synthetic data perform against real defects. We then package the data in a format that can be consumed by Amazon Lookout for Vision (steps 7-8).

Training 72

Training Data Examples Automotive 72

AWS Machine Learning

SEPTEMBER 6, 2022

When most people think of using machine learning (ML) with audio data, the use case that usually comes to mind is transcription , also known as speech-to-text. Using audio data with machine learning. The first step in detecting audio events is understanding how audio data is represented. The following image shows an example.

Training 75

Training Examples Data Measurement 75