Technical How-to Archives - Page 5 of 9

Utilize Amazon Comprehend to identify attempts at email phishing.

Amazon Comprehend, Artificial Intelligence, Intermediate (200), Technical How-to, UncategorizedJune 6, 202431Views 0Likes 0Comments

Phishing is a method employed by malicious actors to trick individuals into revealing sensitive data such as usernames, passwords, and credit card details. Various methods such as email, telephone, or text messages are used to present themselves as a trustworthy entity. Despite traditional approaches to detect email phishing, emerging trends are harder to handle with…

Simplify the creation and launch of customized models for Amazon Bedrock using Terraform, optimizing it with Provisioned Throughput.

AI/ML, Amazon Bedrock, Amazon Machine Learning, Artificial Intelligence, AWS SDK for Python, Generative AI, Generative BI, Technical How-to, UncategorizedJune 5, 202434Views 0Likes 0Comments

Prioritizing Staff welfare: A Cutting-Edge Strategy Using Generative AI and Amazon SageMaker Canvas

Amazon SageMaker, Amazon SageMaker Canvas, Amazon SageMaker Data Wrangler, Generative AI, Intermediate (200), Technical How-to, UncategorizedJune 4, 202434Views 0Likes 0Comments

The Falcon 2 11B can now be obtained on Amazon’s SageMaker JumpStart.

AIML, Amazon SageMaker, Amazon SageMaker JumpStart, Announcements, Machine learning, SageMaker Jumpstart, Technical How-to, UncategorizedJune 1, 202439Views 0Likes 0Comments

Utilizing AWS HealthOmics and Amazon SageMaker for pre-training genetic language models

Amazon Machine Learning, Artificial Intelligence, AWS HealthOmics, Expert (400), Technical How-to, UncategorizedJune 1, 202435Views 0Likes 0Comments

Genomic language models represent a significant development in genomics, interpreting vast amounts of genomic data and allowing scientists to extract valuable insights that contribute to personalized treatment methods, mutation identification, and gene function discovery. In particular, the pre-training of the genomic language model, HyenaDNA, using genomic data in the AWS Cloud, holds immense potential for…

Complete LLM training on groups of instances exceeding 100 nodes utilizing AWS Trainium.

Amazon EC2, AWS Neuron, AWS Trainium, Best Practices, distributed training, Neuron, Technical How-to, UncategorizedMay 30, 202434Views 0Likes 0Comments

Generating style item descriptions by refining a visual-language model using SageMaker and Amazon Bedrock.

Advanced (300), Amazon Bedrock, Amazon SageMaker, Generative AI, Technical How-to, UncategorizedMay 23, 202431Views 0Likes 0Comments

Creating high-quality product descriptions for millions of products is a significant challenge in online retail. Machine learning (ML) and natural language processing (NLP) technologies can automate this task, vastly improving the searchability of products and increasing customer satisfaction. This article presents a method of predicting domain-specific product attributes from product images with a fine-tuned Vision-Language…

Creating workflows for Generative AI prompt chaining with human involvement.

Amazon Bedrock, AWS Step Functions, Best Practices, Generative AI, Technical How-to, UncategorizedMay 18, 202437Views 0Likes 0Comments

Generative AI is a type of artificial intelligence that utilizes machine learning models and large amounts of data to create new content such as conversations, images, videos, and music. Generative AI works through foundation models (FMs), large pre-trained models capable of performing a variety of tasks based on input prompts. Large Language Models (LLMs), a class…

LotteON’s construction of a custom recommendation system utilizing Amazon SageMaker and MLOps.

Amazon API Gateway, Amazon SageMaker, AWS CodeBuild, AWS Lambda, Experience-Based Acceleration, Technical How-to, UncategorizedMay 17, 202431Views 0Likes 0Comments

Speed up NLP interpretation using ONNX Runtime on AWS Graviton processors

Amazon EC2, Graviton, Intermediate (200), Machine learning, Natural language processing, Technical How-to, UncategorizedMay 16, 202437Views 0Likes 0Comments

ONNX is an open-source machine learning framework, offering interoperability across various platforms. It collaborates with ONNX Runtime, the runtime engine for model inference and training. AWS Graviton3 processors are specifically tailored for machine learning tasks and support a series of instructions to optimize performance. The ONNX Runtime 1.17.0 release integrates some of these instructions, improving…