paper : https://pages.cs.wisc.edu/~akella/CS744/F17/838-CloudPapers/Kafka.pdf
[Read More]
Useful Tools
Starting your Jupyter Notebook with double-click
https://blog.modelworks.ch/starting-your-jupyter-notebook-with-a-double-click/
[Read More]
OCR
The four stages derived from existing STR models are as follows: Transformation (Trans.) normalizes the input text image using the Spatial Transformer Network (STN [12]) to ease downstream stages. Feature extraction (Feat.) maps the input image to a representation that focuses on the attributes relevant for character recognition, while suppressing...
[Read More]
Bertology
Personal Notes
paper: https://arxiv.org/pdf/1502.03167.pdf%27
[Read More]
Statistical foundations of modern ML
Must know stats for ML practitioners: Know what a p-value is and its limitations in decisions. Linear regression and its assumptions. When to use different statistical distributions. How an effect size impacts results/decisions. Mean, variance for Normal, Uniform, Poisson. Sampling techniques and common designs (e.g. A/B). Bayes’ theorem (applied calculations)....
[Read More]