clm_4102e6bcWe 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 … (excerpt)
arXiv 1703.03400 · cs.LG cs.AI cs.CV
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
clm_4102e6bcWe 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 … (excerpt)
clm_507eeee1We demonstrate that this approach leads to state-of-the-art performance on two fewshot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with … (excerpt)
clm_6308b866In this work, we propose a meta-learning algorithm that is general and model-agnostic, in the sense that it can be directly applied to any learning problem and model that is … (excerpt)
res_f5640da1From a dynamical systems standpoint, our learning process can be viewed as maximizing the sensitivity of the loss functions of new tasks with respect to the parameters: when the sensitivity … (excerpt)
clm_42d21d2bWe demonstrate the algorithm on different model types, including fully connected and convolutional networks, and in several distinct domains, including few-shot regression, image classification, and reinforcement learning.
clm_dfad2922Our evaluation shows that our meta-learning algorithm compares favorably to state-of-the-art one-shot learning methods designed specifically for supervised classification, while using fewer parameters, but that it can also be readily … (excerpt)
res_c714a628In effect, we will aim to find model parameters that are sensitive to changes in the task, such that small changes in the parameters will produce large improvements on the … (excerpt)
res_d1d0d4fd(3) Can a model learned with MAML continue to improve with additional gradient updates and/or examples?
res_9e562dceFurthermore, we observe both in the qualitative and quantitative results (Figure 3 and Appendix B) that the model learned with MAML continues to improve with additional gradient steps, despite being … (excerpt)
res_47063ac0This improvement suggests that MAML optimizes the parameters such that they lie in a region that is amenable to fast adaptation and is sensitive to loss functions fromp(T ), as … (excerpt)
clm_87572713MAML achieves results that are comparable to or outperform state-of-the-art convolutional and recurrent models.
res_d3b15eb0However, as shown in the comparison, MAML significantly outperforms memory-augmented networks and the meta-learner LSTM on 5-way Omniglot and MiniImagenet classification, both in the 1-shot and 5-shot case.
res_47d6892dThe results in Figure 5 show that MAML learns a model that can quickly adapt its velocity and direction with even just a single gradient update, and continues to improve … (excerpt)
clm_a74949f5The results also show that, on these challenging tasks, the MAML initialization substantially outperforms random initialization and pretraining.
clm_c60c834cLastly, since our method merely produces a weight initialization, adaptation can be performed with any amount of data and any number of gradient steps, though we demonstrate state-of-the-art results on … (excerpt)
res_feeb11abTo achieve averaging in parameter space, we sequentially trained 500 separate models on 500 tasks drawn from p(T ).
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1703.03400) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.