TensorFlow Training Course

Highlights

• Explore TensorFlow Basics

• Create and initialise variables and data 

• Use TensorFlow Mechanics to build graphs and train the model 

• Gain knowledge about the perceptron learning algorithm and binary classification

• Support vector machines: kernels and margin classification 

• Acquire knowledge in feedforward and feedback Artificial Neural Networks

• Learn Convolutional Neural Networks: explore model architecture and training 

Course Details

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

TensorFlow Mechanics

• Inputs and Placeholders

• Build the Graph

  • Inference

  • Loss

  • Training

•          Train the model

  • The graph

  • The session

  • Train loop

• Evaluate the model.

  • Build the eval graph

  • Eval output

The perceptron

• Activation functions

• The perceptron learning algorithm

• Binary classification with the perceptron

• Document classification with the perceptron

• Limitations of the perceptron

Support Vector Machines

• Kernels and the kernel trick.

• Maximum margin classification and support vectors

Artificial Neural Networks

• 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

Convolutional Neural Networks

• Goals

• Model architecture

• Principles

• Code organization

• Launching and training the model.

• Evaluating a model. 

Who should attend

The course is aimed at delegates with a Mathematical and/or Data Science/ML background. Good programming knowledge, especially using the Python programming language. Some experience and familiarity with the Pandas, Numpy and MatPlotLib python libraries for data analysis.