paper-with-me

홈 › Papers

Accelerating Neural Self-Improvement via Bootstrapping

2023-05-02 · Kazuki Irie, Jürgen Schmidhuber

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 NK 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 NK examples, using only NK examples. Promising results are obtained on the standard Mini-ImageNet dataset. Our code is public.

📄 PDF Abstract BibTeX arXiv:2305.01547

Code (1)

idsia/modern-srwm 공식 구현 pytorch

Tasks

Few-Shot LearningMeta-Learning

Similar Papers 제목 키워드 기반

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

2023-03-23 · ICCV 2023 1 · Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran 외

Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e., they maximize the representation similarity of a given image's augmented views. Recent work NNCLR goes beyond the…

Contrastive LearningRepresentation Learning

Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping

2024-02-12 · Haoyu Wang, Guozheng Ma, Ziqiao Meng, Zeyu Qin 외

Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a single round, which …

In-Context Learning

Smart Sampling: Self-Attention and Bootstrapping for Improved Ensembled Q-Learning

2024-05-14 · Muhammad Junaid Khan, Syed Hammad Ahmed, Gita Sukthankar

We present a novel method aimed at enhancing the sample efficiency of ensemble Q learning. Our proposed approach integrates multi-head self-attention into the ensembled Q networks while bootstrapping the state-action pai…

Q-Learning

Accelerating Inverse Reinforcement Learning with Expert Bootstrapping

2024-02-04 · David Wu, Sanjiban Choudhury

Existing inverse reinforcement learning methods (e.g. MaxEntIRL, $f$-IRL) search over candidate reward functions and solve a reinforcement learning problem in the inner loop. This creates a rather strange inversion where…

Imitation LearningMuJoCoreinforcement-learningReinforcement Learning

Effective Self-Training for Parsing

2006-06-01 · NAACL 2006 6 · David McClosky, Eugene Charniak, and Mark Johnson

We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the…

Constituency Parsing