Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Finn, C., Abbeel, P., & Levine, S. July, 2017. arXiv:1703.03400 [cs]
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks [link]Paper  doi  abstract   bibtex   
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.
@misc{finn_model-agnostic_2017,
	title = {Model-{Agnostic} {Meta}-{Learning} for {Fast} {Adaptation} of {Deep} {Networks}},
	url = {http://arxiv.org/abs/1703.03400},
	doi = {10.48550/arXiv.1703.03400},
	abstract = {We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.},
	language = {en},
	urldate = {2023-07-05},
	publisher = {arXiv},
	author = {Finn, Chelsea and Abbeel, Pieter and Levine, Sergey},
	month = jul,
	year = {2017},
	note = {arXiv:1703.03400 [cs]},
	keywords = {\#Few-shot, \#ICML{\textgreater}17, \#Meta-learning, /unread, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, ⭐⭐⭐⭐⭐},
}

Downloads: 0