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 108

Natural Language Processing AWS Data Science Database 108

Snorkel AI

DECEMBER 12, 2023

Building these applications presents many challenges. In this example, we will outline how Google Cloud solutions and Snorkel AI”s data development platform can be combined to develop highly accurate, large-scale intent-matching capabilities inside of DialogflowCX for a typical retail bank support use case.

AI 59

AI AI Machine Learning Machine Learning 59

AWS Machine Learning Blog

APRIL 29, 2024

These powerful models are designed to handle complex tasks with high performance and strong accuracy, making them suitable for real-world applications. These can be used to instruct any other application or tool. About the authors Pradeep Prabhakaran is a Customer Solutions Architect at Cohere.

AWS 81

AWS Natural Language Processing Database ML 81

AWS Machine Learning Blog

SEPTEMBER 8, 2023

Amazon Rekognition makes it easy to add image analysis capability to your applications without any machine learning (ML) expertise and comes with various APIs to fulfil use cases such as object detection, content moderation, face detection and analysis, and text and celebrity recognition, which we use in this example.

K-nearest Neighbors 91

K-nearest Neighbors AWS ML ML 91

Heartbeat

MAY 9, 2023

This advanced library, which is frequently used in applications that process and understand large volumes of text, is now integrated with Comet ML , a very useful experiment monitoring tool! Emotion Recognition Dataset Overview The dataset to be used in the application described in the blog post was created for an emotion classification task.

Natural Language Processing 59

Natural Language Processing ML ML Machine Learning 59

AWS Machine Learning Blog

NOVEMBER 10, 2023

We are witnessing a rapid increase in the adoption of large language models (LLM) that power generative AI applications across industries. Organizations looking to use LLMs to power their applications are increasingly wary about data privacy to ensure trust and safety is maintained within their generative AI applications.

AI 90

AI AI AWS ML 90

Snorkel AI

JANUARY 11, 2023

Every minute, another 500 hours are added to the platform. Time to label training data for ML solution was prohibitively slow given the reliance on external data labeling services that required multiple iterations. Using AI to help customers optimize ad spending and maximize their reach on YouTube.

Data Warehouse 52

Data Warehouse Natural Language Processing Data Scientist Data Quality 52

IBM Journey to AI blog

FEBRUARY 22, 2024

IBM’s Enterprise Cloud for Regulated Industries Building on our expertise working with enterprise clients in industries such as financial services, government, healthcare and telco, we saw the need for a cloud platform designed with the unique needs of these heavily regulated industries in mind.

Database 76

Database Cloud Computing Cloud Data AI 76

Smart Data Collective

AUGUST 2, 2019

These companies need to understand the website accessibility requirements in the jurisdictions they serve, as well as the solutions that AI offers. This applies to all websites, mobile apps, and online applications. AI Presents Real Solutions to eCommerce Companies Looking to Improve Website Accessibility.

AI 70

AI AI Machine Learning Machine Learning 70

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. Their research, set to be published this year, demonstrates an ML solution, built with Google's TensorFlow, that can identify pills with 99.8% certainty when used correctly.

ML 72

ML ML Deep Learning Deep Learning 72

AWS Machine Learning Blog

AUGUST 15, 2023

Previous studies have shown how RAG can be applied to provide a Q&A solution connecting with an enterprise’s private domain knowledge. The RAG-based video/audio question answering solution can potentially solve business problems of locating training and reference materials that are in the form of non-text content.

AWS 72

AWS ML ML AI 72

IBM Journey to AI blog

OCTOBER 11, 2023

This case study may inspire other businesses to explore similar solutions for improving customer engagement and satisfaction. It’s a testament to their commitment to enhancing the customer experience and streamlining operations.

87

87

How to Learn Machine Learning

APRIL 23, 2023

Facial recognition: Social media platforms like Facebook and Google identify people through facial recognition, which works based on narrow artificial intelligence. Autonomous vehicles: autonomous or self-driving cars are another example of the application of narrow AI. The analyzed data is again used for making predictions.

Artificial Intelligence 52

Artificial Intelligence Artificial Intelligence AI AI 52

AWS Machine Learning Blog

APRIL 17, 2023

Amazon SageMaker Data Wrangler is a service in Amazon SageMaker Studio that provides an end-to-end solution to import, prepare, transform, featurize, and analyze data using little to no coding. Solution overview Data Wrangler provides over 40 built-in connectors for importing data. Choose Python (Pandas).

AWS 82

AWS ML ML Python 82

Explosion

MARCH 17, 2019

To use the pretrained weights, we can simply pass them as an argument to spacy train : python -m spacy train en /models/ /corpora/PTB_SD_3_3_0/train.gold.json /corpora/PTB_SD_3_3_0/dev.gold.json --n-examples 100 --pipeline parser --init-tok2vec pretrain-nv-model999.bin Not all matrix multiplication solutions are created equal.

Python 52

Python Natural Language Processing Deep Learning Deep Learning 52