Difference between revisions of "Machine Learning Resources"

From Wiki2
Jump to navigation Jump to search
Line 3: Line 3:
 
* [https://pytorch.org/docs/stable/torch.html Pytorch]
 
* [https://pytorch.org/docs/stable/torch.html Pytorch]
 
* [https://scikit-learn.org/stable/ Scikit-learn]
 
* [https://scikit-learn.org/stable/ Scikit-learn]
 +
* [https://www.tensorflow.org/probability Tensorflow Probability]
 +
* [https://github.com/tensorflow/ranking Tensorflow Rank] (TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform. It contains the following components:
 +
Commonly used loss functions including pointwise, pairwise, and listwise losses.
 +
Commonly used ranking metrics like Mean Reciprocal Rank (MRR) and Normalized Discounted Cumulative Gain (NDCG).
 +
Multi-item (also known as groupwise) scoring functions.
 +
LambdaLoss implementation for direct ranking metric optimization.
 +
Unbiased Learning-to-Rank from biased feedback data.)
 +
 
* [https://docs.databricks.com/applications/deep-learning/index.html Deep learning Databricks]
 
* [https://docs.databricks.com/applications/deep-learning/index.html Deep learning Databricks]
  

Revision as of 08:17, 10 July 2019

Key Frameworks:

Commonly used loss functions including pointwise, pairwise, and listwise losses. Commonly used ranking metrics like Mean Reciprocal Rank (MRR) and Normalized Discounted Cumulative Gain (NDCG). Multi-item (also known as groupwise) scoring functions. LambdaLoss implementation for direct ranking metric optimization. Unbiased Learning-to-Rank from biased feedback data.)

Neural Network Interpretability


Python Notebook Examples

Image Quality Assessment


Transfer Learning