AWS Machine Learning Blog

JANUARY 12, 2024

This enables applications such as semantic search, Retrieval Augmented Generation (RAG), topic modeling, and text classification. In this post, we showcase an application that can search and query across financial news in different languages using Cohere’s Embed and Rerank models with Amazon Bedrock.

Natural Language Processing 113

Natural Language Processing AWS Data Science Database 113

AssemblyAI

APRIL 3, 2024

Pero hay no idea lo que me iba a encontrar yo en ese toilet. En number dos, lo primero que tú dices en mi cocina es good morning. Así que no estoy en el toilet doing my business cuando escucho una woman screaming from el toilet de Alao. Thank you for all this comida que tu pones en nuestra family table.

AI 139

AI AI Analytics Analytics 139

AWS Machine Learning Blog

APRIL 7, 2023

infer_model_id = "tensorflow-tc-bert-en-uncased-L-12-H-768-A-12-2" infer_model_version= "*" endpoint_name = name_from_base(f"jumpstart-example-{infer_model_id}") # Retrieve the inference docker container uri. infer-tensorflow-tc-bert-en-uncased-L-12-H-768-A-12-2.tar.gz Run the train_model.py amazonaws.com/tensorflow-inference:2.8-cpu

AWS 80

AWS Clustering ML ML 80

IBM Journey to AI blog

OCTOBER 11, 2023

In the IBM Cloud catalog , search Event Notifications > Event Notifications. Let’s look at how to set up and use the Custom Email Destination feature in IBM Cloud Event Notifications. Step 1: Create an IBM Cloud Event Notifications service instance Log in to your IBM Cloud account. Provide a Service name. Select a resource group.

92

92

AWS Machine Learning Blog

NOVEMBER 21, 2023

Different downstream applications are made possible by text embeddings, including similarity searching, information retrieval, recommendations and personalization, multilingual translations, and more. In this post, we use huggingface-sentencesimilarity-bge-large-en as an example. English BGE Base En 21.2 English BGE Large En 34.7

Machine Learning 87

Machine Learning Machine Learning AWS ML 87

How to Learn Machine Learning

APRIL 15, 2023

By analysing a customer’s search history, previous bookings, and social media activity, AI can recommend travel destinations, activities, and accommodations that are tailored to the customer’s interests. La entrada Artificial Intelligence in Tourism Industry se publicó primero en How to Learn Machine Learning.

Artificial Intelligence 52

Artificial Intelligence Artificial Intelligence AI AI 52

Explosion

OCTOBER 1, 2019

You can now write commands like the following, just as you would when training the parser, entity recognizer or tagger: python -m spacy train en /output /train /dev --pipeline textcat --textcat-arch simple_cnn --textcat-multilabel You can read more about the data format required in the API docs. To fix these problems, v2.2 seconds) v2.2.0

Algorithm 59

Algorithm Natural Language Processing Python Data Science 59

How to Learn Machine Learning

DECEMBER 4, 2022

It also offers a search engine for finding code snippets and examples. La entrada How is AI Being Used To Write Code se publicó primero en How to Learn Machine Learning. The bots can be trained to write code in multiple languages, including Java, Python, and JavaScript. JTBD is a great way to create a balance while working.

AI 52

AI AI Artificial Intelligence Artificial Intelligence 52

AWS Machine Learning Blog

DECEMBER 5, 2023

Enterprises may want to add custom metadata like document types (W-2 forms or paystubs), various entity types such as names, organization, and address, in addition to the standard metadata like file type, date created, or size to extend the intelligent search while ingesting the documents.

AWS 98

AWS ML ML Natural Language Processing 98

Flipboard

NOVEMBER 20, 2023

When a user asks a question, it searches the vector database and retrieves documents that are most similar to the user’s query. We use two AWS Media & Entertainment Blog posts as the sample external data, which we convert into embeddings with the BAAI/bge-small-en-v1.5 Deploy the BAAI/bge-small-en-v1.5 embeddings.

AWS 128

AWS Database Machine Learning Machine Learning 128

AWS Machine Learning Blog

AUGUST 14, 2023

positive Multilingual question answering (English to Chinese) Explain to me in Traditional Chinese what is the backpropagation 梯度反向传播算法是一种机器学习算法，用于训练人工神经网络。该算法使用梯度下降来最小化损失函数。 Code generation Write a binary search tree with O(log(n)) computational complexity. Intent: show pictures ### Search all these files as fast as possible.

AWS 71

AWS Natural Language Processing Machine Learning Machine Learning 71

AWS Machine Learning Blog

SEPTEMBER 8, 2023

OpenSearch Service allows you to store vectors and other data types in an index, and offers rich functionality that allows you to search for documents using vectors and measuring the semantical relatedness, which we use in this post. You then filter by the Person entity, which you use as an input search parameter.

K-nearest Neighbors 96

K-nearest Neighbors AWS ML ML 96

Hacker News

APRIL 5, 2023

This breach has been flagged as "sensitive" which means it is not publicly searchable , rather you must demonstrate you control the email address being searched before the results are shown. The email address search is what HIBP is so well known for and that's obviously what will help you understand if you've been impacted.

Analytics 177

Analytics Analytics 177

AWS Machine Learning Blog

MARCH 28, 2024

Solution overview In this post, we demonstrate the use of Mixtral-8x7B Instruct text generation combined with the BGE Large En embedding model to efficiently construct a RAG QnA system on an Amazon SageMaker notebook using the parent document retriever tool and contextual compression technique. We use an ml.t3.medium

AWS 111

AWS Machine Learning Machine Learning AI 111

Mlearning.ai

JULY 5, 2023

Let’s build a Power App to use Azure Open AI ChatGPT to summarize the results from Cognitive Search What’s needed Register for Azure Open AI —  [link] Once got approved create a azure open ai resource in Azure portal Select region as East US At the time of writing this article gpt4, gpt3.5-turbo

Azure 52

Azure ML ML AI 52

AWS Machine Learning Blog

AUGUST 15, 2023

Efficiently discovering and searching for specific content within digital assets is crucial for businesses to optimize workflows, streamline collaboration, and deliver relevant content to the right audience. In reality, most of the digital assets lack informative metadata that enables efficient content search.

AWS 73

AWS ML ML AI 73

Dataconomy

MAY 5, 2023

AI search engines Consensus AI Google Bard Komo AI You.com Bing AI AI interior design tools Reimagine Home AI Interior AI Other AI tools Poised AI Uberduck AI Spotify AI DJ Pimeyes Microsoft Security Copilot OpenAI ChatGPT plugins Otter.ai  Adobe Podcast AI Do you want more tools? Need some one-on-one help from a robot creative?

AI 195

AI AI Artificial Intelligence Artificial Intelligence 195

Heartbeat

DECEMBER 13, 2023

I need to search for the Sacramento Kings win-loss record for the 2022-2023 season. I need to search for information about the Apple TV show Foundation and then return the answer in all lower case. How to Create and Implement Custom Tools in LangChain Photo by Todd Quackenbush on Unsplash Preliminaries %%capture !pip

Deep Learning 52

Deep Learning Deep Learning ML ML 52

Google Research AI blog

FEBRUARY 28, 2023

We partnered with ENS , a university in France, to help fund scholarships for students to train through research. We continued to grow open source datasets in 2022, for example, in natural language processing and vision, and expanded our global index of available datasets in Google Dataset Search.

ML 72

ML ML Deep Learning Deep Learning 72

Data Science 101

OCTOBER 12, 2023

Very cool what types of information are you searching for? Are your results used to impact search results? Meanwhile you can check Microsoft Learn’s tutorials: learn.microsoft.com/en-us… How can people find you elsewhere online? I use PyTorch for that. That’s one of the main uses.

Azure 64

Azure Computer Science Computer Science Clustering 64

AWS Machine Learning Blog

APRIL 29, 2024

To find the Command R and R+ models, search for “Command R” in the search box located at the top left of the SageMaker JumpStart landing page. If you don’t see these models, ensure you have the latest SageMaker Studio version by shutting down and restarting Studio Classic Apps.

AWS 85

AWS Natural Language Processing Database ML 85

IBM Journey to AI blog

SEPTEMBER 20, 2023

a global brand), sent en masse to millions of people in hope that some small percentage of recipients will take the bait. According to a report from Omdia, hackers craft convincing spear phishing emails after about 100 minutes of general Google searching. Spear phishing is targeted phishing.

Artificial Intelligence 107

Artificial Intelligence Artificial Intelligence Machine Learning Machine Learning 107

Towards AI

FEBRUARY 13, 2024

execute()​ list_of_topic_id = [] for item in videos_ids["items"]: id_video = item['id']['videoId'] list_of_topic_id.append(id_video)​ return list_of_topic_id Note: the q parameter defined to search for a specific term. params: list_of_video_id: this is the list of video ids.

Python 86

Python Clustering AI AI 86

AWS Machine Learning Blog

JUNE 7, 2023

billion-parameter model using the wikicorpus-en dataset. RJ is an engineer in Search M5 team leading the efforts for building large scale deep learning systems for training and inference. Abhinandan Patni is a Senior Software Engineer at Amazon Search.

AWS 67

AWS Clustering Deep Learning Deep Learning 67

Explosion

APRIL 27, 2023

Or perhaps you’re parsing news articles in search of mergers and acquisitions and trying to understand the connections between various companies and individuals. Consider, for instance, a sentence with a Person entity and a Location entity: is the person living in that location, are they just visiting or are the two mentions unrelated?

Machine Learning 69

Machine Learning Machine Learning Deep Learning Deep Learning 69

Hacker News

SEPTEMBER 5, 2023

” Monahan has been documenting the crypto thefts via Twitter/X since March 2023, frequently expressing frustration in the search for a common cause among the victims. Then on Aug. “So you just crunch and crunch and crunch with GPUs, with a priority list of vaults you target.”

Computer Science 182

Computer Science Computer Science Analytics Analytics 182

Explosion

DECEMBER 14, 2021

nlp] lang = "en" pipeline = ["sentencizer","tok2vec","ner"] [components.tok2vec] source = ${paths.ner_model} component = "tok2vec" [components.ner] source = ${paths.ner_model} component = "ner" For the Benepar to work, we add an additional sentencizer component that creates sentence boundaries. [nlp] ✨ Our custom_code.py

Clustering 52

Clustering Machine Learning Machine Learning Natural Language Processing 52

AWS Machine Learning Blog

NOVEMBER 10, 2023

client('comprehend') response = client.detect_toxic_content( TextSegments=[{"Text": "What is the capital of France?"}, {"Text": "Where do I find good baguette in France?"}], LanguageCode='en') print(response) Prompt safety classification Prompt safety classification with Amazon Comprehend helps classify an input text prompt as safe or unsafe.

AI 94

AI AI AWS ML 94

AWS Machine Learning Blog

SEPTEMBER 6, 2023

You can also find other four model variants by choosing Explore all Text Generation Models or searching for llama in the search box. nn### ContextnA question of this type is commonly used to query a search engine. For more information about version updates, refer to Shut down and Update Studio Apps.

ML 97

ML ML Machine Learning Machine Learning 97

DrivenData Labs

DECEMBER 10, 2023

We eventually narrowed in on a set of related tasks that researchers described as major pain points in this type of work, including summarization of existing research, identifying relevant papers, extracting the right keywords or search terminology, finding the leading experts in a field, and more. bge-small-en-v1.5 bge-small-en-v1.5

AI 147

AI AI Natural Language Processing Artificial Intelligence 147

Explosion

NOVEMBER 21, 2019

import spacy from spacy.pipeline import EntityRuler nlp = spacy.blank("en") ruler = EntityRuler(nlp).from_disk("./fashion_brands_patterns.jsonl") As this was a quick project, and we didn’t collect separate development and evaluation sets, we performed only a limited set of experiments, and avoided detailed hyperparameter searches.

Natural Language Processing 52

Natural Language Processing Data Scientist Machine Learning Machine Learning 52

Hacker News

FEBRUARY 2, 2023

I’d already done a little bit of investigation of reversible rules, but this led to a big search for reversible rules —which would later come in handy for thinking about microscopically reversible processes and thermodynamics. Back in 1983 I already had pretty efficient code for searching for structures in class 4 cellular automata.

Machine Learning 166

Machine Learning Machine Learning Algorithm Analytics 166