Deep Learning with Tensorflow
This repo is a resource for my Deep Learning with Tensorflow talk. It contains all of the code that was demonstrated as well as the deck.
Inspiration
This talk is inspired by the venerable mnist dataset! It is also inspired by a silly nine squares image problem.
The purpose of this silly problem is to provide the basic intution behind models, cost, accuracy, and optimization principles behind machine learning.
Overview
Deep Learning Principles
- input
- model function
- cost function
- optimization method
Tensorflow
- Tensors
- DataSets
- Models
- Loss (or Cost)
- Optimization