Continuous learning in single-incremental-task scenarios
نویسندگان
چکیده
منابع مشابه
Reinforcement Learning in Non-Stationary Continuous Time and Space Scenarios
In this paper we propose a neural architecture for solving continuous time and space reinforcement learning problems in non-stationary environments. The method is based on a mechanism for creating, updating and selecting partial models of the environment. The partial models are incrementally estimated using linear approximation functions and are built according to the system’s capability of mak...
متن کاملFine-Tuning Deep Neural Networks in Continuous Learning Scenarios
The revival of deep neural networks and the availability of ImageNet laid the foundation for recent success in highly complex recognition tasks. However, ImageNet does not cover all visual concepts of all possible application scenarios. Hence, application experts still record new data constantly and expect the data to be used upon its availability. In this paper, we follow this observation and ...
متن کاملHandling Continuous-Valued Attributes in Incremental First-Order Rules Learning
Machine Learning systems are often distinguished according to the kind of representation they use, which can be either propositional or first-order logic. The framework working with first-order logic as a representation language for both the learned theories and the observations is known as Inductive Logic Programming (ILP). It has been widely shown in the literature that ILP systems have limit...
متن کاملIncremental Social Learning in Swarm Intelligence Algorithms for Continuous Optimization
Swarm intelligence is the collective problem-solving behavior of groups of animals and artificial agents. Often, swarm intelligence is the result of self-organization, which emerges from the agents’ local interactions with one another and with their environment. Such local interactions can be positive, negative, or neutral. Positive interactions help a swarm of agents solve a problem. Negative ...
متن کاملMulti-task Learning for Continuous Control
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision. In addition, most reinforcement learning research on multitask learning has bee...
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: Neural Networks
سال: 2019
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2019.03.010