Ben Chuanlong Du's Blog

It is never too late to learn.

Log Softmax vs Softmax

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

The difference betwen Log Softmax and Softmax should be understood together with the loss function.

References

https://discuss.pytorch.org/t/what-is-the-difference-between-log-softmax-and-softmax/11801

https://discuss.pytorch.org/t/logsoftmax-vs-softmax/21386

https …

Models for Computer Vision

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

torchvision has implementation of popular deep learning models for computer vision.

ResNet-50

ResNet-50 is a 50-layer Residual Neural Network.

ResNet 101

ResNet-101 is a 101-layer Residual Neural Network.

ResNet 152

ResNet-152 …

Interpretation of Neural Networks

** Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

** Please refer to the Interpretations section of the wiki page Deep Learning.

https://github.com/slundberg/shap#methods-unified-by-shap

https://arxiv.org/pdf/1802.03888.pdf

https://github.com/slundberg/shap

References …

Distributed Training of Models on Spark

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

XGBoost

http://www.legendu.net/misc/blog/use-xgboost-with-spark/

LightGBM

http://www.legendu.net/misc/blog/use-lightgbm-with-spark/

BigDL

MMLSpark

Apache Ray

You can run Apache Ray on top of Spark via analytics-zoo …

Clustering Algorithms in Machine Learning

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Centroid-based Clustering

  • K-means Clustering

  • K-medians Clustering

  • K-mediods Clustering

Hierarchical Clustering

  • Agglomerative Hierarchical Clustering

  • Divisive Hierarchical Clustering

Partional Clustering

Metrics for Machine Learning

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Accuracy

Precision/Recall

F1

Matthrews Correlation Coefficient (MCC)

ROC/AUC

Mean Absolute Error (MAE)

Mean Squared Error (MSE)

Root-mean-square Error (RMSE)