Neural Networks Fundamentals using TensorFlow as Example

TensorFlow Basics

• Creation, Initializing, Saving, and Restoring TensorFlow variables
• Feeding, Reading and Preloading TensorFlow Data
• How to use TensorFlow infrastructure to train models at scale
• Visualizing and Evaluating models with TensorBoard

• Inputs and Placeholders
• Build the GraphS
  • Inference
  • Loss
  • Training
• Train the Model
  • The Graph
  • The Session
  • Train Loop
• Evaluate the Model
  • Build the Eval Graph
  • Eval Output

• Activation functions
• The perceptron learning algorithm
• Binary classification with the perceptron
• Document classification with the perceptron
• Limitations of the perceptron

• Kernels and the kernel trick
• Maximum margin classification and support vectors

• Nonlinear decision boundaries
• Feedforward and feedback artificial neural networks
• Multilayer perceptrons
• Minimizing the cost function
• Forward propagation
• Back propagation
• Improving the way neural networks learn

• Goals
• Model Architecture
• Principles
• Code Organization
• Launching and Training the Model
• Evaluating a Model