Communications of the ACM

Building Intelligent Agents with Neuro-Symbolic Concepts

The agent acquires a vocabulary of neuro-symbolic concepts for objects, relations, and actions, represented through a ...
VentureBeat

Google’s new AI training method helps small models tackle complex reasoning

Researchers at Google Cloud and UCLA have proposed a new reinforcement learning framework that significantly improves the ability of language models to learn very challenging multi-step reasoning ...
C&EN

Optimizing Multi-Task Learning with Evolutionary Relatedness Metrics for Enhanced QSAR-Based Natural Product Activity Prediction

Article subjects are automatically applied from the ACS Subject Taxonomy and describe the scientific concepts and themes of the article. A few public databases provide biological activity data for ...
Frontiers

Seismic first break picking based on multi-task learning

Introduction: Seismic first break (FB) picking helps us with near surface tomography, microseismic detection among other tasks. Using image semantic segmentation (ISS) networks to do so has been a hot ...
WAND

Human trafficking task force to be based in Decatur

DECATUR, Ill. (WAND) — Law enforcement efforts to crack down on human trafficking down are being beefed up in Central Illinois. The Decatur City Council backing a resolution to establish the Illinois ...
Frontiers

The effects of the implementation order of implicit and explicit learning methods on learners' task enjoyment and motor skill acquisition

Purpose: This study aimed to explore the effect of the order of two learning methods (one based on implicit and another on explicit learning) on students' enjoyment and ability to acquire motor skills ...
IEEE

Task Augmentation-Based Meta-Learning Segmentation Method for Retinopathy

Abstract: Deep learning (DL) requires large amounts of labeled data, which is extremely time-consuming and labor-intensive to obtain for medical image segmentation ...