A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Thomas Gruber
Gruber treats formal ontologies as designed artifacts and proposes design criteria for building reusable, shareable knowledge specifications.
Unknown
The paper introduces correlation congruence, a knowledge distillation method that transfers correlation patterns between teacher and student networks to improve model compression.
Lin Zhang, Lei Zhang, Xuanqin Mou, et al.
FSIM proposes a full-reference image quality metric using phase congruency and gradient magnitude as complementary features, achieving state-of-the-art correlation with human perception.
Aniruddha Dutta, Saket Kumar, Meheli Basu
This paper demonstrates that a GRU model with recurrent dropout outperforms existing models for Bitcoin price prediction and can yield financial gains when used in simple trading strategies.