practicalai 0.0.1.dev4 on PyPI

https://goku.me/practicalAI

Running the notebooks

Access the notebooks at https://goku.me/practicalAI or in the notebooks directory in this repo.
Replace https://github.com/ with https://colab.research.google.com/github/ in the notebook URL or use this Chrome extension to do it with one click.
Sign into your Google account.
Click the COPY TO DRIVE button on the toolbar. This will open the notebook on a new tab.

Rename this new notebook by removing the Copy of part in the title.
Run the code, make changes, etc. and it's all automatically saved to you personal Google Drive.

Contributing to notebooks

Make your changes and download the Google colab notebook as an .ipynb file.

Go to https://github.com/GokuMohandas/practicalAI/tree/master/notebooks
Click on Upload files.

Upload the .ipynb file.
Write a detailed commit title and message.
Name your branch as appropriately.
Click on Propose changes.

TODO

Notebook	Completed	ToDo
00_Notebooks	text cells code cells saving notebook
01_Python	lists, tuples, dicts functions classes
02_NumPy	indexing arithmetic advanced
03_Pandas	loading data exploratory analysis preprocessing feature engineering saving data
04_Linear_Regression	overview training data scikit interpretability regularization categorical	polynomial normal equation
05_Logistic_Regression	overview training data scikit metrics metrics interpretability cross validation	interaction terms odds ratio coordinate descent
06_Random_Forests	decision tree training data scikit interpretability random forests interpretability grid search	regression example gini vs. entropy
07_PyTorch	tensors indexing gradients CUDA	customized function
08_Multilayer_Perceptron	overview training data linear model non-linear model tensorboardd activation functions initialize weights overfitting dropout	interpretability dropconnect PReLU
09_Data_and_Models	data quality quantity modeling
10_Object_Oriented_ML	overview set up data Vocabulary Vectorizer Dataset Model Trainer Inference	tqdm notebook
11_Convolutional_Neural_Networks	overview filters pooling char-level conv	n-gram interpretability
12_Embeddings	overview learning embeddings pretrained embeddings using embeddings freezing embeddings	interpretable conv filters contextualized embeddings
13_Recurrent_Neural_Networks	overview sequenitial data gradient issues BiRNN document classification layernorm	interpretability
14_Advanced_RNNs	conditioned RNN attention char-level embeddings	BLEU Beam search Hierarchical softmax QRNN
15_Computer_Vision	classification transfer learning	various data sizes segmentation activation maps
16_Highway_and_Residual_Networks
17_Time_Series_Analysis
18_Kmeans_Clustering
19_Topic_Modeling
20_Auto_Encoders
21_Generative_Adversarial_Networks
22_Recommendation_Systems
23_Pretrained_Language_Models
24_Multitask_Learning
25_Low_Shot_Learning
26_Reinforcement_Learning

practicalai
Release 0.0.1.dev4

Release 0.0.1.dev4

0.0.1.dev4

0.0.1.dev3

0.0.1.dev2

0.0.1.dev1

0.0.1

Documentation

Running the notebooks

Contributing to notebooks

TODO

Stats

Development practices

Releases

Contributors

practicalai Release 0.0.1.dev4

Release 0.0.1.dev4 Toggle Dropdown 0.0.1.dev4 0.0.1.dev3 0.0.1.dev2 0.0.1.dev1 0.0.1

Documentation

Running the notebooks

Contributing to notebooks

TODO

Stats

Development practices

Releases

Contributors

practicalai
Release 0.0.1.dev4

Release 0.0.1.dev4

0.0.1.dev4

0.0.1.dev3

0.0.1.dev2

0.0.1.dev1

0.0.1