TensorFlow training course

Gain a comprehensive introduction to TensorFlow - Google's open source software library for Deep Learning.

NEXT COURSE 18 November (3 days £2500 + VAT) BOOK NOW

JBI training course London UK

  • Explore Tensorflow Basics: Create and Initialize variables and data 
  • Utilise TensorFlow Mechanics to build graphs and train the model 
  • Gain knowledge about perceptron learning algorithm and Binary classification
  • Support Vector Machines: Karnels and margin classification 
  • Acquire knowledge in Feedforward and feedback artificial neural networks
  • Learn Convolutional Neural Networks: Explore Model architecture and training 

FULL COURSE DETAILS

Our TensorFlow™ training course for Deep Learning will give delegates a comprehensive introduction to this Google open source software library, used by Data Science professionals  for numerical computation using data flow graphs.

Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them.

The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well.


FULL COURSE DETAILS
JBI training course London UK
JBI training course London UK

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. 


FULL COURSE DETAILS

Related Courses

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. 
 
Course Updates & Newsletter
 
 

Receive the latest version of this course by email & subscribe to our Newsletter



CONTACT
0800 028 6400

enquiries@jbinternational.co.uk

SHARE

Corporate Policies     Terms & Conditions
JB International Training Ltd  -  Company number 08458005

Registered address 1345 High Road, London, N20 9HR