Papers with Code 아카이브

Meta-Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 3
평가표: 4
보존된 평가 기록: 13

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

<span style="color:grey; opacity: 0.6">( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/allenai/macaw

Language Models are Few-Shot Learners

https://github.com/allenhaozhu/ease

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

https://github.com/alrope123/prompt-waywardness

Making Pre-trained Language Models Better Few-shot Learners

https://github.com/amajee11us/smile-fsod

Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

https://github.com/amazon-research/nearest-neighbor-crosslingual-classification

Nearest Neighbour Few-Shot Learning for Cross-lingual Classification

https://github.com/amazon-research/uniform-episodic-sampling

Uniform Sampling over Episode Difficulty

https://github.com/amazon-science/alexa-teacher-models

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

https://github.com/amurthy1/dagan

Data Augmentation Generative Adversarial Networks

https://github.com/amurthy1/dagan_torch

Data Augmentation Generative Adversarial Networks

https://github.com/amzn/metalearn-leap

Transferring Knowledge across Learning Processes

https://github.com/andris955/diplomaterv

Learning to Multi-Task by Active Sampling

https://github.com/anguyen8/deepface-emd

DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning

https://github.com/anguyen8/face-vit

DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning

https://github.com/aniket03/keras_compact_bilnear_CNN

Compact Bilinear Pooling

https://github.com/antaradas94/MAML-waste-classification

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/anusfoil/llaqo

Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities

https://github.com/aozhongzhang/magr

LLaMA: Open and Efficient Foundation Language Models

https://github.com/aravindMahadevan/metaLearningAlgos

On First-Order Meta-Learning Algorithms

https://github.com/arazd/ProgressivePrompts

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/ard-srp/qml_analysis

TensorFlow Quantum: A Software Framework for Quantum Machine Learning

https://github.com/ardakdemir/my_bert_ner

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

https://github.com/arghosh/noisy_label_pretrain

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

https://github.com/arkilpatel/compositional-generalization-seq2seq

Human few-shot learning of compositional instructions

https://github.com/artemZholus/variational_memory_addressing

Variational Memory Addressing in Generative Models

https://github.com/artix41/ALFI-pytorch

Recurrent machines for likelihood-free inference

https://github.com/aryaze/testpilot

An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation

https://github.com/asadovsky/nn

Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing

https://github.com/asagar60/Siamese-Neural-Networks-for-One-shot-Image-Recognition

https://github.com/asahi417/lmppl

Language Models are Few-Shot Learners

https://github.com/asahi417/relbert

Language Models are Few-Shot Learners

https://github.com/asap7772/fewshot-preference-optimization

FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users

https://github.com/ash3n/Latent-Similarity

Prototypical Networks for Few-shot Learning

https://github.com/ash3n/Meta-Gradients

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

https://github.com/ash3n/Meta-SGD

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

https://github.com/ash3n/Meta-SGD-TF

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

https://github.com/ash3n/One-shot-Memory-Augmented-NN

One-shot Learning with Memory-Augmented Neural Networks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.