<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Randy DeFauw &#8211; Noise</title>
	<atom:link href="https://noise.getoto.net/author/randy-defauw/feed/" rel="self" type="application/rss+xml" />
	<link>https://noise.getoto.net</link>
	<description>The collective thoughts of the interwebz</description>
	<lastBuildDate>Wed, 13 Mar 2024 16:49:47 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=6.8.2</generator>
	<item>
		<title>Build a RAG data ingestion pipeline for large-scale ML workloads</title>
		<link>https://noise.getoto.net/2024/03/13/build-a-rag-data-ingestion-pipeline-for-large-scale-ml-workloads/</link>
		
		<dc:creator><![CDATA[Randy DeFauw]]></dc:creator>
		<pubDate>Wed, 13 Mar 2024 16:49:47 +0000</pubDate>
				<category><![CDATA[Advanced (300)]]></category>
		<category><![CDATA[Amazon Machine Learning]]></category>
		<category><![CDATA[Amazon OpenSearch Service]]></category>
		<category><![CDATA[RDS for PostgreSQL]]></category>
		<guid isPermaLink="false">http://noise.getoto.net/?guid=147cd97351c293873b5dc1a9b61ae878</guid>

					<description><![CDATA[For building any generative AI application, enriching the large language models (LLMs) with new data is imperative. This is where the Retrieval Augmented Generation (RAG) technique comes in. RAG is a machine learning (ML) architecture that uses external documents (like Wikipedia) to augment its knowledge and achieve state-of-the-art results on knowledge-intensive tasks. For ingesting these […]]]></description>
		
		
		<enclosure url="" length="0" type="" />

			</item>
		<item>
		<title>Minimizing Dependencies in a Disaster Recovery Plan</title>
		<link>https://noise.getoto.net/2022/01/26/minimizing-dependencies-in-a-disaster-recovery-plan/</link>
		
		<dc:creator><![CDATA[Randy DeFauw]]></dc:creator>
		<pubDate>Tue, 25 Jan 2022 23:29:06 +0000</pubDate>
				<category><![CDATA[Amazon Route 53]]></category>
		<category><![CDATA[Architecture]]></category>
		<category><![CDATA[AWS Identity and Access Management (IAM)]]></category>
		<category><![CDATA[AWS Organizations]]></category>
		<category><![CDATA[Disaster Recovery]]></category>
		<guid isPermaLink="false">http://noise.getoto.net/?guid=f4e56df4370e9885ab51fc6f1758d6d6</guid>

					<description><![CDATA[The Availability and Beyond whitepaper discusses the concept of static stability for improving resilience. What does static stability mean with regard to a multi-Region disaster recovery (DR) plan? What if the very tools that we rely on for failover are themselves impacted by a DR event? In this post, you’ll learn how to reduce dependencies […]]]></description>
		
		
		<enclosure url="" length="0" type="" />

			</item>
		<item>
		<title>Applying Federated Learning for ML at the Edge</title>
		<link>https://noise.getoto.net/2021/12/09/applying-federated-learning-for-ml-at-the-edge/</link>
		
		<dc:creator><![CDATA[Randy DeFauw]]></dc:creator>
		<pubDate>Thu, 09 Dec 2021 16:29:42 +0000</pubDate>
				<category><![CDATA[Amazon Elastic Container Service]]></category>
		<category><![CDATA[Amazon Sagemaker]]></category>
		<category><![CDATA[Architecture]]></category>
		<category><![CDATA[AWS Fargate]]></category>
		<category><![CDATA[AWS IoT Core]]></category>
		<category><![CDATA[AWS IoT Greengrass]]></category>
		<category><![CDATA[AWS Step Functions]]></category>
		<guid isPermaLink="false">http://noise.getoto.net/?guid=43f8dae90dd6407e3106f3c707d7d0bf</guid>

					<description><![CDATA[Federated Learning (FL) is an emerging approach to machine learning (ML) where model training data is not stored in a central location. During ML training, we typically need to access the entire training dataset on a single machine. For purposes of performance scaling, we divide the training data between multiple CPUs, multiple GPUs, or a […]]]></description>
		
		
		<enclosure url="" length="0" type="" />

			</item>
		<item>
		<title>Configure Amazon EMR Studio and Amazon EKS to run notebooks with Amazon EMR on EKS</title>
		<link>https://noise.getoto.net/2021/09/25/configure-amazon-emr-studio-and-amazon-eks-to-run-notebooks-with-amazon-emr-on-eks/</link>
		
		<dc:creator><![CDATA[Randy DeFauw]]></dc:creator>
		<pubDate>Fri, 24 Sep 2021 21:25:20 +0000</pubDate>
				<category><![CDATA[Amazon Elastic Kubernetes Service]]></category>
		<category><![CDATA[Amazon EMR]]></category>
		<guid isPermaLink="false">http://noise.getoto.net/?guid=f4ce5a3348bd4bea175b7963ead24932</guid>

					<description><![CDATA[Amazon EMR on Amazon EKS provides a deployment option for Amazon EMR that allows you to run analytics workloads on Amazon Elastic Kubernetes Service (Amazon EKS). This is an attractive option because it allows you to run applications on a common pool of resources without having to provision infrastructure. In addition, you can use Amazon […]]]></description>
		
		
		<enclosure url="" length="0" type="" />

			</item>
		<item>
		<title>Emerging Solutions for Operations Research on AWS</title>
		<link>https://noise.getoto.net/2021/09/03/emerging-solutions-for-operations-research-on-aws/</link>
		
		<dc:creator><![CDATA[Randy DeFauw]]></dc:creator>
		<pubDate>Fri, 03 Sep 2021 17:14:45 +0000</pubDate>
				<category><![CDATA[Amazon Braket]]></category>
		<category><![CDATA[Amazon DynamoDB]]></category>
		<category><![CDATA[Amazon Elasticsearch Service]]></category>
		<category><![CDATA[Amazon Sagemaker]]></category>
		<category><![CDATA[Architecture]]></category>
		<category><![CDATA[AWS Glue]]></category>
		<category><![CDATA[AWS Lambda]]></category>
		<category><![CDATA[Expert (400)]]></category>
		<category><![CDATA[reinforcement-learning]]></category>
		<guid isPermaLink="false">http://noise.getoto.net/?guid=21bab6665a43a060591c238bef73000c</guid>

					<description><![CDATA[Operations research (OR) uses mathematical and analytical tools to arrive at optimal solutions for complex business problems like workforce scheduling. The mathematical techniques used to solve these problems, such as linear programming and mixed-integer programming, require the use of optimization software (solvers).  There are several popular and powerful solvers available, ranging from commercial options like […]]]></description>
		
		
		<enclosure url="" length="0" type="" />

			</item>
	</channel>
</rss>

<!--
Performance optimized by W3 Total Cache. Learn more: https://www.boldgrid.com/w3-total-cache/

Object Caching 35/125 objects using Memcached
Page Caching using Disk: Enhanced 
Lazy Loading (feed)
Database Caching using Memcached

Served from: noise.getoto.net @ 2026-03-10 21:17:58 by W3 Total Cache
-->