TensorFlow is a graph computation library designed by engineers at Google, and is starting to power many of Google's recent advances in deep learning and artificial intelligence.
A graph computation library has two steps. They are listed below:
- Defining the sequence (or more complex graphs) of operations that take the input data, operate on it, and convert to outputs.
- Compute on the graph obtained from step 1 with a given input.
Many programmers don't use this type of programming day-to-day, but most of them interact with a related system that does. Relational databases, specifically SQL-based ones, use a similar concept called the declarative paradigm. While a programmer might define a SELECT query on a database with a WHERE clause, the database interprets that and creates an optimised query based on a number of factors, such as whether the WHERE clause is applied to a primary key, the format the data is stored in, and other factors. The programmer defines what...