#concept-learning News & Analysis

5 articles tagged with #concept-learning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AIBullisharXiv – CS AI · Mar 46/105

🧠

CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning

Researchers introduce CORE (Concept-Oriented REinforcement), a new training framework that improves large language models' mathematical reasoning by bridging the gap between memorizing definitions and applying concepts. The method uses concept-aligned quizzes and concept-primed trajectories to provide fine-grained supervision, showing consistent improvements over traditional training approaches across multiple benchmarks.

AIBullisharXiv – CS AI · Feb 277/106

🧠

Abstracted Gaussian Prototypes for True One-Shot Concept Learning

Researchers introduce Abstracted Gaussian Prototypes (AGP), a new framework for one-shot concept learning that can classify and generate visual concepts from a single example. The system uses Gaussian Mixture Models and variational autoencoders to create robust prototypes without requiring pre-training, achieving human-level performance on generative tasks.

AIBullishOpenAI News · Nov 77/107

🧠

Learning concepts with energy functions

Researchers developed an energy-based AI model that can learn spatial concepts like 'near' and 'above' from just five demonstrations using 2D point sets. The model demonstrates cross-domain transfer capabilities, applying concepts learned in 2D particle environments to solve 3D physics-based robotics tasks.

$NEAR

AINeutralarXiv – CS AI · 4d ago6/10

🧠

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

Researchers introduce FaCT, a new approach for explaining neural network decisions through faithful concept-based explanations that don't rely on restrictive assumptions about how models learn. The method includes a new evaluation metric (C²-Score) and demonstrates improved interpretability while maintaining competitive performance on ImageNet.

AIBullishOpenAI News · Feb 155/105

🧠

Interpretable machine learning through teaching

Researchers have developed a machine learning method that enables AIs to teach each other using examples that are also interpretable by humans. The approach automatically identifies the most informative examples to convey concepts, such as selecting optimal images to represent dogs, and has shown effectiveness in teaching both artificial intelligence systems.