Bayesian Optimization Based Efficient Layer Sharing for Incremental Learning
نویسندگان
چکیده
منابع مشابه
Efficient Reinforcement Learning with Bayesian Optimization
OF THE DISSERTATION Efficient Reinforcement Learning with Bayesian Optimization By Danyan Ganjali Doctor of Philosophy in Mechanical and Aerospace Engineering University of California, Irvine, 2016 Professor Athanasios Sideris, Chair A probabilistic reinforcement learning algorithm is presented for finding control policies in continuous state and action spaces without a prior knowledge of the d...
متن کاملEfficient Bayesian Network Learning for System Optimization in Reliability Engineering
We present a new Bayesian network modeling that learns the behavior of an unknown system from real data and can be used for reliability engineering and optimization processes in industrial systems. The suggested approach relies on quantitative criteria for addressing the trade-off between the complexity of a learned model and its prediction accuracy. These criteria are based on measures from In...
متن کاملIncremental methods for Bayesian network structure learning
The incremental learning approach was firstly motivated as the human capability for incorporating knowledge from new experiences worth being programmed into artificial agents. However, nowadays there exist other practical (i.e. industrial) reasons which increase the interest in incremental algorithms. Nowadays, companies from a very wide range of activities store huge amounts of data every day....
متن کاملIncremental Learning for Bayesian Classification of Images
Grouping images into (semantically) meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. In this paper, we develop an incremen-tal learning paradigm for Bayesian classiication of images. Under the Bayesian paradigm, the class-conditional densities are represented in terms of code-book vectors. Learning is thus, incrementa...
متن کاملBayesian Incremental Learning for Deep Neural Networks
In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each time, so one would rather use a previously learned model and the new data to improve performance. However, deep neural networks are prone to getting stuck in a suboptimal solution when trained on only new data as com...
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: Applied Sciences
سال: 2021
ISSN: 2076-3417
DOI: 10.3390/app11052171