Return to page

H2O.ai Blog

Filter By:

13 results Category: Year:
H2O LLM DataStudio: Streamlining Data Curation and Data Preparation for LLMs related tasks
by Shivam Bansal, Sanjeepan Sivapiran, Nishaanthini Gnanavel | June 14, 2023 Data , Data Preparation , H2O LLM Studio , Large Language Models , NLP , h2oGPT

A no-code application and toolkit to streamline data preparation tasks related to Large Language Models (LLMs) H2O LLM DataStudio is a no-code application designed to streamline data preparation tasks specifically for Large Language Models (LLMs). It offers a comprehensive range of preprocessing and preparation functions such as text cl...

Read more
Make with H2O.ai Recap: Getting Started with H2O Document AI
by Blair Averett | August 05, 2022 Deep Learning , H2O Document AI , Make with H2O.ai , NLP

Product Owner, Data Scientist, and Kaggle Grandmaster, Mark Landry presented at the Make with H2O.ai session on getting started with H2O Document AI. The session covered an overview of H2O Document AI , a tool to extract insights and automate document processing. The session also included a product demo, looking at documents as data sets...

Read more
Introducing H2O Hydrogen Torch: A No-code Deep Learning Framework
by Philipp Singer, Yauhen Babakhin | February 17, 2022 Computer Vision , H2O AI Cloud , H2O Hydrogen Torch , NLP , Product Updates

Over and over again we heard from customers, “deep learning is cool, but it’s hard and time consuming.” They kept asking “could someone just make it easier?” In typical “Maker” fashion, you ask, we deliver, H2O Hydrogen Torch . H2O Hydrogen Torch is a new product that enables data scientists and developers to train and deploy state-of-t...

Read more
Improving NLP Model Performance with Context-Aware Feature Extraction
by Jo-Fai Chow | October 08, 2021 H2O AI Cloud , NLP , Technical

I would like to share with you a simple yet very effective trick to improve feature engineering for text analytics. After reading this article, you will be able to follow the exact steps and try it yourself using our H2O AI Cloud .First of all, let’s have a look at the off-the-shelf natural language processing (NLP) recipes in H2O Driver...

Read more
Modèles NLP avec BERT
by Badr Chentouf | September 02, 2020 H2O Driverless AI , NLP

H2O Driverless AI 1.9 vient de sortir, et je vous propose une série d’articles sur les dernières fonctionnalités innovantes de cette solution d’Automated Machine Learning, en commençant par l’implémentation de BERT pour les tâches NLPBERT , ou “Bidirectional Encoder Representations from Transformers” est considéré aujourd’hui comme l’éta...

Read more
Insights From the New 2020 Gartner Magic Quadrant For Cloud AI Developer Services

We are excited to be named a Visionary in the new Gartner Magic Quadrant for Cloud AI Developer Services (Feb 2020), and have been recognized for both our completeness of vision and ability to execute in the emerging market for cloud-hosted artificial intelligence (AI) services for application developers. This is the second Gartner MQ tha...

Read more
AI & ML Platforms: My Fresh Look at H2O.ai Technology

2020: A new year, a new decade, and with that, I’m taking a new and deeper look at the technology H2O.ai offers for building AI and machine learning systems. I’ve been interested in H2O.ai since its early days as a company (it was 0xdata back then) in 2014. My involvement had been only peripheral, but now I’ve begun to work with this comp...

Read more
Grandmaster Series: How a Passion for Numbers Turned This Mechanical Engineer into a Kaggle Grandmaster

In conversation with Sudalai Rajkumar: A Kaggle Double Grandmaster and a Data Scientist at H2O.aiIt is rightly said that one should never seek praise. Instead, let the effort speak for itself. One of the essential traits of successful people is to never brag about their success but instead keep learning along the way. In the data science ...

Read more
Natural Language Processing in H2O’s Driverless AI
by Sanyam Bhutani | November 06, 2019 Community , H2O Driverless AI , H2O World , Makers , NLP

Note: I’d like to thank Grandmaster SRK for a lot of suggestions and corrections with the writeup.Note: All images used here are from the talk. Link to the slides Link to the video Note 2: All of the discussion here is related to NLP. DriverlessAI also supports other domains that are covered in other talks and posts (releasing soon). Driv...

Read more
Detecting Sarcasm is difficult, but AI may have an answer
by Parul Pandey | August 05, 2019 H2O Driverless AI , NLP , Recipes , Technical , Tutorials

Recently, while shopping for a laptop bag, I stumbled upon a pretty amusing customer review: “This is the best laptop bag ever. It is so good that within two months of use, it is worthy of being used as a grocery bag.” The innate sarcasm in the review is evident as the user isn’t happy with the quality of the bag. However, as the sentence...

Read more
How This AI Tool Breathes New Life Into Data Science

Ask any data scientist in your workplace. Any Data Science Supervised Learning ML/AI project will go through many steps and iterations before it can be put in production. Starting with the question of “Are we solving for a regression or classification problem?” Data Collection & Curation Are there Outliers? What is the Distribu...

Read more
Automatic Feature Engineering for Text Analytics - The Latest Addition to Our Kaggle Grandmasters' Recipes
by Jo-Fai Chow, Sudalai Rajkumar | September 12, 2018 Data Science , GPU , H2O Driverless AI , NLP

According to Kaggle’s ‘The State of Machine Learning and Data Science ’ survey , text data is the second most used data type at work for data scientists. There are a lot of interesting text analytics applications like sentiment prediction, product categorization, document classification and so on. In the latest version (1.3) of our Driver...

Read more
Stacked Ensembles and Word2Vec now available in H2O!

Prepared by: Erin LeDell and Navdeep Gill MathJax.Hub.Config({ tex2jax: {inlineMath: [['$','$'], ['\\(','\\)']]} }); Stacked Ensembles ensemble <- h2o.stackedEnsemble(x = x, y = y, training_frame = train, base_models = my_models) Python:ensemble = H2OStackedEnsembleEstimator(base_models=my_models) ensemble.train(x=x, y=y, training...

Read more

No results found. 
Please modify your search.