J Ürgen Schmidhuber, Kazuki Irie
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Few-shot learning with sequence-processing neural networks (NNs) has recently attracted a new wave of attention in the context of large language models. In the standard N -way K-shot learning setting, an NN is explicitly optimised to learn to classify unlabelled inputs by observing a sequence of N K labelled examples. This pressures the NN to learn a learning algorithm that achieves optimal performance, given the limited number of training examples. Here we study an auxiliary loss that encourages further acceleration of few-shot learning, by applying recently proposed bootstrapped meta-learning to NN few-shot learners: we optimise the K-shot learner to match its own performance achievable by observing more than N K examples, using only N K examples. Promising results are obtained on the standard Mini-ImageNet dataset. Our code is public. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2305.01547")
get_code_for_paper("2305.01547")
have("2305.01547")
Connect an agent — have() is free.