Deep Learning with TensorFlow - bespoke

• Statistics
• Python
• (optional) A laptop with NVIDIA GPU that supports CUDA 8.0 and cuDNN 5.1, with 64-bit Linux installed

TensorFlow is a 2nd Generation API of Google's open source software library for Deep Learning. The system is designed to facilitate research in machine learning, and to make it quick and easy to transition from research prototype to production system.

Audience

This course is intended for engineers seeking to use TensorFlow for their Deep Learning projects

After completing this course, delegates will:

• understand the theory and practice behind different types of neural networks
• be able to set up a sample Deep Learning neural network using TensorFlow

Introduction to Neural Networks

• What are Neural Networks
• Neural Networks vs regression models
• Mathematical foundations and learning mechanisms
• Constructing an artificial neural network
• Neural nodes and connections
• Neurons, layers, and input and output data
• Single layer perceptrons
• Supervised and unsupervised learning
• Feedforward and feedback neural networks
• Forward propagation and back propagation
• Long short-term memory (LSTM)
• Recurrent Neural Networks in practice
• Convulational Neural Networks in practice
• Machine learning and Deep Learning
• Applications for Deep Learning
• Improving the way neural networks learn
• Creating a Deep Learning network with TensorFlow

Working with TensorFlow

• Preparing the data
  • Download
  • Inputs and placeholders
• Building the graph
  • Inference
  • Loss
  • Training
• Training the model
  • The graph
  • The session
  • Train loop
• Evaluate the model
  • Building the Eval Graph
  • Evaluating with Eval Output
• Training models at scale
• Visualizing and evaluating models with TensorBoard