Papers with Code 아카이브

Gaussian Processes

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 1
평가표: 1
보존된 평가 기록: 1

Gaussian Processes is a powerful framework for several machine learning tasks such as regression, classification and inference. Given a finite set of input output training data that is generated out of a fixed (but possibly unknown) function, the framework models the unknown function as a stochastic process such that the training outputs are a finite number of jointly Gaussian random variables, whose properties can then be used to infer the statistics (the mean and variance) of the function at test values of input.

Source: Sequential Randomized Matrix Factorization for Gaussian Processes: Efficient Predictions and Hyper-parameter Optimization

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

UCI Machine Learning Repository

UCI Machine Learning Repository is a collection of over 550 datasets.

MPI FAUST Dataset

Contains 300 scans of 10 people in a wide range of poses together with an evaluation methodology. Source: FAUST: Dataset and Evaluation for 3D Mesh Registration

WHOI-Plankton

WHOI-Plankton is a collection of annotated plankton images. It contains > 3.5 million images of microscopic marine plankton, organized according to category labels provided by researchers at the Woods Hole Oceanographic Institution (WHOI). The images are currently placed into one of 103 categories. Source: WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classification

Photoswitch

A benchmark for molecular machine learning where improvements in model performance can be immediately observed in the throughput of promising molecules synthesized in the lab. Photoswitches are a versatile class of molecule for medical and renewable energy applications where a molecule's efficacy is governed by its electronic transition wavelengths. Source: The Photoswitch Dataset: A Molecular Machine Learning Benchmark for the Advancement of Synthetic Chemistry

Poser

The Poser dataset is a dataset for pose estimation which consists of 1927 training and 418 test images. These images are synthetically generated and tuned to unimodal predictions. The images were generated using the Poser software package. Source: Overlapping Cover Local Regression Machines Image Source: https://www.researchgate.net/figure/Test-data-used-in-the-user-study-Left-the-pose-pictures-shown-to-the-user-Middle-the_fig17_221847487

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