Papers with Code 아카이브
Model Selection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Given a set of candidate models, the goal of Model Selection is to select the model that best approximates the observed data and captures its underlying regularities. Model Selection criteria are defined such that they strike a balance between the goodness of fit, and the generalizability or complexity of the models.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/fabstat/burbank
공식 코드https://github.com/facebookresearch/DomainBed
공식 코드https://github.com/facebookresearch/balancinggroups
공식 코드Simple data balancing achieves competitive worst-group-accuracy
https://github.com/facebookresearch/fjd
공식 코드https://github.com/facebookresearch/glemos
공식 코드GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection
https://github.com/facebookresearch/kats
공식 코드MOSPAT: AutoML based Model Selection and Parameter Tuning for Time Series Anomaly Detection
https://github.com/facebookresearch/qmnist
공식 코드https://github.com/fdschmidt93/free-lunch-xlt
공식 코드Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging
https://github.com/fdschmidt93/ofa-xlt
공식 코드https://github.com/fe1ixxu/mixed-gradient-few-shot
공식 코드https://github.com/ferretdoll/hgr
공식 코드Hologram Reasoning for Solving Algebra Problems with Geometry Diagrams
https://github.com/fjxmlzn/InfoGAN-CR
공식 코드InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
https://github.com/fmfi-compbio/virpool
공식 코드https://github.com/fmohr/lccv
공식 코드Fast and Informative Model Selection using Learning Curve Cross-Validation
https://github.com/fraspass/dcsbm
공식 코드Spectral clustering on spherical coordinates under the degree-corrected stochastic blockmodel
https://github.com/freguglia/mrf2dbayes
공식 코드https://github.com/g-benton/hessian-eff-dim
공식 코드Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
https://github.com/g-walley/cegpy
공식 코드https://github.com/gaabrielfranco/llp-variants-datasets-benchmarks
공식 코드https://github.com/gabb7/ODIN
공식 코드ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems
https://github.com/gaia-vision/gaia-ssl
공식 코드https://github.com/geekan/metagpt
공식 코드SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
https://github.com/geobrain-ai/geogalactica
공식 코드GeoGalactica: A Scientific Large Language Model in Geoscience
https://github.com/gieseke/speedynn
공식 코드Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
https://github.com/gmum/bnn-functional-priors
공식 코드https://github.com/google-research-datasets/Image-Caption-Quality-Dataset
공식 코드Quality Estimation for Image Captions Based on Large-scale Human Evaluations
https://github.com/google-research/pactran_metrics
공식 코드https://github.com/gptune/hybridminimization
공식 코드Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization
https://github.com/granelle/naacl24-user-sim
공식 코드Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation
https://github.com/gravins/dynamic_graph_benchmark
공식 코드https://github.com/gykovacs/maweight
공식 코드https://github.com/h-yu16/domainbed-v2
공식 코드https://github.com/hamilton-health-sciences/ml4h-traq
공식 코드Do Ensembling and Meta-Learning Improve Outlier Detection in Randomized Controlled Trials?
https://github.com/hanklee97121/SUM-SR-5iter
공식 코드Unsupervised Video Summarization via Iterative Training and Simplified GAN
https://github.com/hanmacrad2/SuperSpreadingEpidemicsMCMC
공식 코드A Bayesian Modelling Framework with Model Comparison for Epidemics with Super-Spreading
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.