Duration
28 hours (usually 4 days including breaks)
Requirements
Basic programming skills
Overview
Computer Network ToolKit (CNTK) is Microsoft’s Open Source, Multi-machine, Multi-GPU, Highly efficent RNN training machine learning framework for speech, text, and images.
Audience
This course is directed at engineers and architects aiming to utilize CNTK in their projects.
Course Outline
Getting started
- Setup CNTK on your machine
- Enabling 1bit SGD
- Developing and Testing
- CNTK Production Test Configurations
- How to contribute to CNTK
- Tutorial
- Tutorial II
- CNTK usage overview
- Examples
- Presentations
- Multiple GPUs¹ and machines
Configuring CNTK
- Config file overview
- Simple Network Builder
- BrainScript Network Builder
- SGD block
- Reader block
- Train, Test, Eval
- Top-level configurations
Describing Networks
- Basic concepts
- Expressions
- Defining functions
- Full Function Reference
Data readers
- Text Format Reader
- CNTK Text Format Reader
- UCI Fast Reader (deprecated)
- HTKMLF Reader
- LM sequence reader
- LU sequence reader
- Image reader
Evaluating CNTK Models
- Overview
- C++ Evaluation Interface
- C# Evaluation Interface
- Evaluating Hidden Layers
- C# Image Transforms for Evaluation
Advanced topics
- Command line parsing rules
- Top-level commands
- Plot command
- ConvertDBN command
¹ The topic related to the use of CNTK with a GPU is not available as a part of a remote course. This module can be delivered during classroom-based courses, but only by prior agreement, and only if both the trainer and all participants have laptops with supported NVIDIA GPUs (not provided by NobleProg). NobleProg cannot guarantee the availability of trainers with the required hardware.