Evolving models for incrementally learning emerging activities
نویسندگان
چکیده
منابع مشابه
Incrementally Learning the Hierarchical Softmax Function for Neural Language Models
Neural network language models (NNLMs) have attracted a lot of attention recently. In this paper, we present a training method that can incrementally train the hierarchical softmax function for NNMLs. We split the cost function to model old and update corpora separately, and factorize the objective function for the hierarchical softmax. Then we provide a new stochastic gradient based method to ...
متن کاملEmerging and Evolving Ovarian Cancer Animal Models
Ovarian cancer (OC) is the leading cause of death from a gynecological malignancy in the United States. By the time a woman is diagnosed with OC, the tumor has usually metastasized. Mouse models that are used to recapitulate different aspects of human OC have been evolving for nearly 40 years. Xenograft studies in immunocompromised and immunocompetent mice have enhanced our knowledge of metasta...
متن کاملLearning Boolean Functions Incrementally
Classical learning algorithms for Boolean functions assume that unknown targets are Boolean functions over fixed variables. The assumption precludes scenarios where indefinitely many variables are needed. It also induces unnecessary queries when many variables are redundant. Based on a classical learning algorithm for Boolean functions, we develop two learning algorithms to infer Boolean functi...
متن کاملLearning Strategy Knowledge Incrementally
Modern industrial processes require advanced computer tools that should adapt to the user requirements and to the tasks being solved. Strategy learning consists of automating the acquisition of patterns of actions used while solving particular tasks. Current intelligent strategy learning systems acquire operational knowledge to improve the eeciency of a particular problem solver. However, these...
متن کاملIncrementally Learning Rules for Anomaly Detection
LERAD is a rule learning algorithm used for anomaly detection, with the requirement that all training data has to be present before it can be used. We desire to create rules incrementally, without needing to wait for all training data and without sacrificing accuracy. The algorithm presented accomplishes these goals by carrying a small amount of data between days and pruning rules after the fin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Ambient Intelligence and Smart Environments
سال: 2020
ISSN: 1876-1372,1876-1364
DOI: 10.3233/ais-200566