Carnegie Mellon University

CMU Researchers Open-Source ‘auton-survival’: A Comprehensive Python Code Repository of User-Friendly, Machine Learning Tools for Working with Censored Time-to-Event Data

Machine learning is being used in almost every industry, including healthcare. However, due to the intrinsic complexity of healthcare data, classical machine learning faces...

Researchers From CMU And Stanford Develop OBJECTFOLDER 2.0: A Multisensory Object Dataset For Sim2Real Transfer

Perception and manipulation of a wide array of items are part of our daily activities. The alarm clock looks round and glossy, cutlery clinks...

CMU Researchers Explain the Effectiveness of AutoML for Diverse Tasks Using AutoML Decathlon and NAS-Bench-360

Machine learning (ML) has experienced a sharp increase in popularity and complexity over the past ten years. Improved deep neural networks it is being...

CMU’s New ‘ReStructured Pre-training’ NLP Approach Pretrains Model Over Valuable Restructured Data

Natural language processing (NLP) paradigms are fast developing, progressing from entirely supervised learning through pre-training and fine-tuning and, most recently, pre-training with immediate prediction....

New MIT Research Suggests That Training An AI Model With Mathematically “Diverse” Teammates Can Improve Its Ability To Collaborate With Other AI It Has...

The prevalence of superhuman artificial intelligence (AI) in competitive games such as chess, Atari, StarCraft II, DotA, and poker is growing. Recent advances in deep...

CMU Researchers Propose Deep Attentive VAE: The First Attention-Driven Framework For Variational Inference In Deep Probabilistic Models

This Article is written as a summay by Marktechpost Staff based on the Research Paper 'DEEP ATTENTIVE VARIATIONAL INFERENCE'. All Credit For This Research...

In The Latest AI Research, CMU And Adobe Researchers Propose An Elegant Emsembling Mechanism For GAN Training That Improves FID by 1.5x to 2x...

This Article Is Based On The Research Paper 'Ensembling Off-the-shelf Models for GAN Training'. All Credit For This Research Goes To The Researchers of...

In A Latest ML Research, CMU Researchers Explains The Connection Between MBRL And The World Of BOED By Deriving An Acquisition Function

This Article Is Based On The Research Paper 'An Experimental Design Perspective on Model-Based Reinforcement Learning'. All Credit For This Research Goes To The...

Meta AI and CMU Team Releases New Dataset For Green Hydrogen Fuel To Accelerate Renewable Energy

This Article Is Based On The Meta AI's article 'Accelerating renewable energy with new data set for green hydrogen fuel'. All Credit For This...

CMU Researchers Introduce a Method for Estimating the Generalization Error of Black-Box Deep Neural Networks With Only Unlabeled Data

Take a look at the following fascinating observation. On two identically generated datasets S1 and S2 of the same size, train two networks of...

Researchers From CMU and LinkedIn Open-SourcesĀ The Implementation of PASS (Performance-Adaptive Sampling Strategy) For Deep Learning

Understanding the relationships between entity sets maintained in a database is critical. In this context, an entity is an object or a data component. Entity...

CMU Researchers Open Source ‘PolyCoder’: A Machine Learning-Based Code Generator With 2.7B Parameters

Language models (LMs) are commonly used in natural language literature to assign probabilities to sequences of tokens. LMs have recently demonstrated outstanding performance in...

Recent articles