https://github.com/google-research/google-research/tree/master/muNet
공식 코드An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
Papers with Code 아카이브
Transfer Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 6
- 보존된 평가 기록
- 10
Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.
<span style="color:grey; opacity: 0.6">( Image credit: Subodh Malgonde )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/google-research/google-research/tree/master/non_semantic_speech_benchmark
공식 코드Towards Learning a Universal Non-Semantic Representation of Speech
https://github.com/google-research/google-research/tree/master/social_rl
공식 코드Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
https://github.com/google-research/head2toe
공식 코드Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
https://github.com/google-research/language/tree/master/language/bert_extraction
공식 코드Thieves on Sesame Street! Model Extraction of BERT-based APIs
https://github.com/google-research/magvit
공식 코드https://github.com/google-research/meta-dataset
공식 코드Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
https://github.com/google-research/pactran_metrics
공식 코드https://github.com/google-research/perch
공식 코드Global birdsong embeddings enable superior transfer learning for bioacoustic classification
https://github.com/google-research/perch/tree/main/chirp
공식 코드https://github.com/google-research/prompt-tuning
공식 코드Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
https://github.com/google-research/robopianist
공식 코드RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning
https://github.com/google-research/tapas
공식 코드https://github.com/google-research/text-to-text-transfer-transformer
공식 코드ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
https://github.com/google-research/uda
공식 코드https://github.com/google-research/understanding-transfer-learning
공식 코드https://github.com/google-research/vision_transformer
공식 코드When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
https://github.com/google-research/xtreme
공식 코드XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
https://github.com/google/gematria
공식 코드GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation
https://github.com/google/graph_distillation
공식 코드Graph Distillation for Action Detection with Privileged Modalities
https://github.com/google/next-prediction
공식 코드Peeking into the Future: Predicting Future Person Activities and Locations in Videos
https://github.com/google/uncertainty-baselines
공식 코드Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit
https://github.com/google/vizier
공식 코드https://github.com/goose315/delta
공식 코드DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation
https://github.com/gorkamunoz/RF-Single-Trajectory-Characterization
공식 코드Machine learning method for single trajectory characterization
https://github.com/gortizji/tangent_task_arithmetic
공식 코드Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
https://github.com/grahman20/TLF
공식 코드https://github.com/grammatical/neural-naacl2018
공식 코드Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task
https://github.com/graph-team/apgl4sr
공식 코드https://github.com/grasp-lyrl/deep_reference_priors
공식 코드Deep Reference Priors: What is the best way to pretrain a model?
https://github.com/gregorbachmann/leaveoneout
공식 코드https://github.com/greschal/mbllearning
공식 코드Scalable approach to many-body localization via quantum data
https://github.com/grtzsohalf/SpeechNet-codebase
공식 코드SpeechNet: A Universal Modularized Model for Speech Processing Tasks
https://github.com/gsarti/interpreting-complexity
공식 코드https://github.com/gsasikiran/Comparative-Evaluation-of-Pretrained-Transfer-Learning-Models-on-ASAG
공식 코드Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading
https://github.com/gstoica27/JRRELP
공식 코드Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.