Name		Name	Last commit message	Last commit date
parent directory ..
MNIST_oracle_plsql.ipynb		MNIST_oracle_plsql.ipynb
MNIST_tables.dmp.gz		MNIST_tables.dmp.gz
MNIST_tensorflow_exp_to_oracle.ipynb		MNIST_tensorflow_exp_to_oracle.ipynb
README.md		README.md

README.md

An example of how to build a neural network scoring engine in PL/SQL

In this you will find the support material for the blog entry: https://db-blog.web.cern.ch/blog/luca-canali/2016-07-neural-network-scoring-engine-plsql-recognizing-handwritten-digits
This is an example of how to build and deploy a basic artificial neural network scoring engine using PL/SQL. It is intended for learning purposes, in particular for Oracle practitioners who want a hands-on introduction to neural networks.

File	Short description
MNIST_oracle_plsql.ipynb	How to deploy the neural network scoring engine in PL/SQL.
MNIST_tensorflow_exp_to_oracle.ipynb	Preparation of the neural network Definition and training of the neural network with tensorFlow Extraction of the trained tensors into numpy arrays proof of concept of how to run the scoring engine manually in Python transfer of the tensors and of the test data to Oracle
MNIST_tables.dmp.gz	Tensors and test data produced as described in MNIST_tensorflow_exp_to_oracle.ipynb exported using Oracle datapump utility (expdp version 11.2.0.4)