Introduction
This is my personal notebook for documenting knowledge I picked up as I progress through my career in machine learning. It helps me reinforcing my theoretical understanding of the problems and solutions I have seen.
I wrote majority of the content in Python 2.7 in 2018. Now it's 2022 April, Python 2 has been long deprecated, I am switching to Python 3.8 with TensorFlow 2.8.
My current system setup
- Ubuntu 20.04
- Tensorflow 2.8.*
- Python 3.8.*
- CUDA 11.2
- cuDNN 8.4
- Matplotlib 3.5.*
Some older code will be running on
- Tensorflow 1.15
- Python 2.7.*
- Clustering
- Simple Neural Networks
- Convolutional Neural Networks
- Generative Adversial Networks
- Recurrent Neural Networks
- Random Forest
- Reinforcement Learning
- Natural Language Processing
- Naive Bayesian Networks
- Recommender System
- Transferred Learning
- Machine Learning in Production
If my notebook does not contain any
matplotlib.pyplot
then I can export it as simple text.jupyter nbconvert --to markdown loss_function_overview.ipynb --stdout
Otherwise, I'd need to export differently.
jupyter nbconvert --to markdown loss_function_overview.ipynb
Jupyter notebook uses single dollar sign for inline equations but GitBook uses double dollar sign for inline equations. I need a RegExp that capture and convert.
?
means once or none.\$.?\$
+
means one or more.\$.+\$
The following will capture all
$<some text>$
.^\$.+\$$
Last modified 9mo ago