ML @ CMU

MARCH 30, 2023

This blog post discusses the effectiveness of black-box model explanations in aiding end users to make decisions. The stages of evaluation are adapted from Doshi-Velez and Kim (2017); we introduce an additional stage, use-case-grounded algorithmic evaluations, in a recent Neurips 2022 paper [ 2 ]. Communications of the ACM, 2022.

ML 52

ML Explainability Algorithm Machine Learning 52

AssemblyAI

MARCH 21, 2023

We can get a first glimpse of this impressive growth if we look at the accepted research publications from the last 3 years for both ICLR and NeurIPS, the two major annual conferences which focus on cutting edge AI research. We find that the term Graph Neural Network consistently ranked in the top 3 keywords year over year.

Neural Network 317

Neural Network Deep Learning AI AI 317

Google Research AI blog

FEBRUARY 28, 2023

In 2022, we expanded our research interactions and programs to faculty and students across Latin America , which included grants to women in computer science in Ecuador. See some of the datasets and tools we released in 2022 listed below. We work towards inclusive goals and work across the globe to achieve them.

Robotics 72

Robotics Deep Learning Auto-classification ML 72

AWS Machine Learning Blog

MAY 22, 2023

arXiv preprint arXiv:2210.11416 (2022). [2] He is an active researcher in machine learning and statistical inference and has published many papers in NeurIPS, ICML, ICLR, JMLR, ACL, and EMNLP conferences. Gather some data for your use case, uploaded it to Amazon S3, and use either the Studio UI or the notebook to tune a FLAN T5 model!

Natural Language Processing 89

Natural Language Processing Machine Learning Computational Linguistics NLP 89

BAIR

APRIL 25, 2022

As we will discuss in this blog post, methods that rely on imitation learning are often quite effective when the behavior in the offline dataset consists of some complete trajectories that perform well. These observations validate the findings discussed earlier in the blog post. What explains this difference?

Robotics 130

Robotics Algorithm Explainability 130

The Stanford AI Lab Blog

APRIL 7, 2022

Discovering systematic errors with cross-modal embeddings In this blog post, we introduce Domino, a new approach for discovering systematic errors made by machine learning models. Paper (ICLR 2022) ? In this blog post, we discuss our recent exploration of this question. 2022 ), GEORGE ( Sohoni et al.

Machine Learning 40

Machine Learning Metadata Algorithm Automation 40

AWS Machine Learning Blog

JANUARY 25, 2023

In November 2022, we announced that AWS customers can generate images from text with Stable Diffusion models in Amazon SageMaker JumpStart. He is an active researcher in machine learning and algorithm design and has published papers in EMNLP, ICLR, COLT, FOCS, and SODA conferences.

Deep Learning 72

Deep Learning Python Algorithm Natural Language Processing 72

AWS Machine Learning Blog

APRIL 10, 2023

In November 2022, we announced that AWS customers can generate images from text with Stable Diffusion models using Amazon SageMaker JumpStart. He is an active researcher in machine learning and algorithm design and has published papers in EMNLP, ICLR, COLT, FOCS, and SODA conferences. Alfred Shen is a Senior AI/ML Specialist at AWS.

Algorithm 79

Algorithm Deep Learning Python ML 79

AWS Machine Learning Blog

NOVEMBER 14, 2023

Inference example with and without fine-tuning The following table contains the results of the Mistral 7B model fine-tuned with SEC filing documents of Amazon from 2021–2022. He is an active researcher in machine learning and statistical inference, and has published many papers in NeurIPS, ICML, ICLR, JMLR, ACL, and EMNLP conferences.

Natural Language Processing 94

Natural Language Processing Python Machine Learning Algorithm 94

Sebastian Ruder

JANUARY 24, 2022

Consequently, 2021 saw much discussion of best practices and ways in which we can reliably evaluate such models going forward, which I cover in this blog post. An art scene emerged around the most recent generation of generative models (see this blog post for an overview). In Proceedings of ICLR 2021. Kolesnikov, A., Melnick, L.,

NLP 52

NLP ML BERT Computational Linguistics 52

Marek Rei

OCTOBER 4, 2019

Graph of conference submission counts, by Grzegorz Chrupała These trends can also be seen in the blog post by the ACL 2019 Chairs. ACL 2022 offers an opportunity to correct that with a call recently sent out to the members’ list for hosts in the Europe/Middle East/Africa region in July or August 2022.

NLP 52

NLP Computational Linguistics Automation AI 52

AWS Machine Learning Blog

SEPTEMBER 6, 2023

He is an active researcher in machine learning and algorithm design and has published papers in EMNLP, ICLR, COLT, FOCS, and SODA conferences. He is an active researcher in machine learning and statistical inference, and has published many papers in NeurIPS, ICML, ICLR, JMLR, ACL, and EMNLP conferences.

Auto-complete 97

Auto-complete Machine Learning ML Python 97

AWS Machine Learning Blog

FEBRUARY 20, 2023

In November 2022, we announced that AWS customers can generate images from text with Stable Diffusion models in Amazon SageMaker JumpStart. He is an active researcher in machine learning and algorithm design and has published papers in EMNLP, ICLR, COLT, FOCS, and SODA conferences.

Algorithm 79

Algorithm Python Machine Learning Natural Language Processing 79