Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments: Difference between revisions
Jump to navigation
Jump to search
Line 1: | Line 1: | ||
= Introduction = | = Introduction = | ||
Typically, the basic goal of machine learning is to train a model to perform a task. In Meta-learning, the goal is to train a model to perform the task of training a model to perform a task. Hence in this case the term "Meta-Learning" has the exact meaning you would expect | Typically, the basic goal of machine learning is to train a model to perform a task. In Meta-learning, the goal is to train a model to perform the task of training a model to perform a task. Hence in this case the term "Meta-Learning" has the exact meaning you would expect; the word "Meta" has the precise function of introducing a layer of abstraction. | ||
The meta-learning task can be made more concrete by a simple example. Consider the CIFAR-100 classification task that we used for our data competition. | |||
In this paper, a probabilistic framework for meta learning is derived then applied to tasks involving simulated robotic spiders. This framework generalizes the typical machine learning set up using Markov Decision Processes. | In this paper, a probabilistic framework for meta learning is derived then applied to tasks involving simulated robotic spiders. This framework generalizes the typical machine learning set up using Markov Decision Processes. |
Revision as of 09:50, 12 March 2018
Introduction
Typically, the basic goal of machine learning is to train a model to perform a task. In Meta-learning, the goal is to train a model to perform the task of training a model to perform a task. Hence in this case the term "Meta-Learning" has the exact meaning you would expect; the word "Meta" has the precise function of introducing a layer of abstraction.
The meta-learning task can be made more concrete by a simple example. Consider the CIFAR-100 classification task that we used for our data competition.
In this paper, a probabilistic framework for meta learning is derived then applied to tasks involving simulated robotic spiders. This framework generalizes the typical machine learning set up using Markov Decision Processes.