Results 131 to 140 of about 15,121 (239)

TACOS: Task Agnostic Continual Learning in Spiking Neural Networks [PDF]

open access: yesarXiv
Catastrophic interference, the loss of previously learned information when learning new information, remains a major challenge in machine learning. Since living organisms do not seem to suffer from this problem, researchers have taken inspiration from biology to improve memory retention in artificial intelligence systems.
arxiv  

The K‐ras mutation pattern in pancreatic ductal adenocarcinoma usually is identical to that in associated normal, hyperplastic, and metaplastic ductal epithelium

open access: bronze, 1999
Jütta Lüttges   +5 more
openalex   +1 more source

Importance of the brain corticosteroid receptor balance in metaplasticity, cognitive performance and neuro-inflammation

open access: yesFrontiers in neuroendocrinology (Print), 2018
E. R. Kloet   +4 more
semanticscholar   +1 more source

Stress: metaplastic effects in the hippocampus

open access: hybrid, 1998
Jeansok J. Kim, Kenneth S. Yoon
openalex   +1 more source

Cell Lineage Specificity of Newly Raised Monoclonal Antibodies Against Gastric Mucins in Normal, Metaplastic, and Neoplastic Human Tissues and Their Application to Pathology Diagnosis [PDF]

open access: bronze, 2001
Hiroyoshi Ota   +11 more
openalex   +1 more source

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks [PDF]

open access: yesarXiv
Neuromorphic computing with spiking neural networks is promising for energy-efficient artificial intelligence (AI) applications. However, different from humans who continually learn different tasks in a lifetime, neural network models suffer from catastrophic forgetting.
arxiv  

Sarcoma and Sarcomatous Metaplastic Carcinoma of the Breast [PDF]

open access: bronze, 2001
Sang Han Yu   +8 more
openalex   +1 more source

Continual Learning for Autonomous Robots: A Prototype-based Approach [PDF]

open access: yesarXiv
Humans and animals learn throughout their lives from limited amounts of sensed data, both with and without supervision. Autonomous, intelligent robots of the future are often expected to do the same. The existing continual learning (CL) methods are usually not directly applicable to robotic settings: they typically require buffering and a balanced ...
arxiv  

Home - About - Disclaimer - Privacy