AssemblyAI

APRIL 3, 2024

Universal-1 reduces hallucination rate by 30% over a widely used open-source model, Whisper Large-v3, providing users with confidence in the results we deliver. 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. Emilito. ¿Number

AI 139

AI AI Analytics Analytics 139

Hacker News

MARCH 8, 2024

LINUX AND OPEN SOURCE NEWS PODCAST: Listen to the latest Linux and open source news, with more in depth coverage, and ad-free! GET TLE MERCH Support the channel AND get cool new gear: https://the-linux-experiment.creator-spring.com/ ?️ https://podcast.thelinuxexp.com ?

140

140

Flipboard

NOVEMBER 20, 2023

Retrieval Augmented Generation (RAG) allows you to provide a large language model (LLM) with access to data from external knowledge sources such as repositories, databases, and APIs without the need to fine-tune it. Deploy the BAAI/bge-small-en-v1.5 embeddings. embeddings model to a SageMaker real-time endpoint.

AWS 128

AWS Database Machine Learning Machine Learning 128

Google Research AI blog

FEBRUARY 28, 2023

Posted by Posted by Leslie Yeh, Director, University Relations (This is Part 9 in our series of posts covering different topical areas of research at Google. We partnered with ENS , a university in France, to help fund scholarships for students to train through research. You can find other posts in the series here.)

ML 72

ML ML Deep Learning Deep Learning 72

AWS Machine Learning Blog

JANUARY 12, 2024

This enables applications such as semantic search, Retrieval Augmented Generation (RAG), topic modeling, and text classification. Finding the answer to a question across a variety of sources and documents is time-intensive and tedious work. We use SageMaker this time: query = "Are companies ready for the next down market?"

Natural Language Processing 116

Natural Language Processing AWS Data Science Database 116

AWS Machine Learning Blog

MARCH 28, 2024

With the advancements being made with LLMs like the Mixtral-8x7B Instruct , derivative of architectures such as the mixture of experts (MoE) , customers are continuously looking for ways to improve the performance and accuracy of generative AI applications while allowing them to effectively use a wider range of closed and open source models.

AWS 115

AWS Machine Learning Machine Learning AI 115

Data Science 101

OCTOBER 12, 2023

My data sources are usually news, logs and web documents. Once the data is processed I do machine learning: clustering, topic finding, extraction, and classification. Meanwhile you can check Microsoft Learn’s tutorials: learn.microsoft.com/en-us… How can people find you elsewhere online?

Azure 64

Azure Computer Science Computer Science Clustering 64

AWS Machine Learning Blog

AUGUST 15, 2023

The response from the chatbot will be able to directly answer the question and also include the links to the source videos with the specific timestamp of the contents that are most relevant to the user’s request. Users can get answers generated by LLMs and relevant sources with timestamps. Each paragraph focuses on the same topic.

AWS 73

AWS ML ML AI 73

AWS Machine Learning Blog

FEBRUARY 9, 2024

AWS CDK is an open source software development framework to model and provision your cloud application resources using familiar programming languages. In addition, it aggregates the invocations per model and costs by each team. You can deploy the solution in your own account using the AWS CDK.

AWS 130

AWS Machine Learning Machine Learning Python 130

DrivenData Labs

DECEMBER 10, 2023

Team / participant Features Models Data sources NASAPalooza Paper search, paper recommendation, doc upload, paper summarization, chatbot, people search, keyword extraction, topic trends, dataset analysis GPT-3.5 bge-small-en-v1.5 bge-small-en-v1.5 bge-small-en-v1.5

AI 147

AI AI Natural Language Processing Artificial Intelligence 147

AWS Machine Learning Blog

SEPTEMBER 6, 2023

Llama 2 was pre-trained on 2 trillion tokens of data from publicly available sources. A pupil of the École des Chartes, his thesis was called Vues sur l’histoire de l’organisation judiciaire en France du IXe au XIIIe siècle considérée au point de vue des juridictions extraordinaires and he got the diploma of “archiviste paléographe” in 1874.

ML 101

ML ML Machine Learning Machine Learning 101

Hacker News

FEBRUARY 2, 2023

The closest it gets is a chapter on CP violation (AKA time-reversal violation)—a longtime favorite topic of mine—but from a very particle-physics point of view. The physicists I was around mostly weren’t too interested in such topics—though Richard Feynman was something of an exception. No statistical mechanics. SMP Version 1.0

Machine Learning 163

Machine Learning Machine Learning Algorithm Analytics 163

ML Review

MAY 3, 2018

This topic, when broached, has historically been a source of contention among linguists, neuroscientists and AI researchers. We will continue to experiment with scope and timelines, to understand how best to convey topics to the reader. Source : Originally created by Dr Mary Allen and available from her site [9].

Deep Learning 52

Deep Learning Deep Learning Natural Language Processing Machine Learning 52