NVIDIA DEEP LEARNING INSTITUTE

TEACHING YOU TO SOLVE PROBLEMS WITH DEEP LEARNING

Online Self-Paced Labs

The NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve the world’s most challenging problems with deep learning.

Through self-paced online labs and instructor-led workshops, DLI provides training on the latest techniques for designing, training, and deploying neural networks across a variety of application domains. Explore widely used open-source frameworks as well as NVIDIA’s latest GPU-accelerated deep learning platforms.

Create an account with Qwiklabs to experience free and low-cost online deep learning labs below.


Applications of Deep Learning with Caffe, Theano, and Torch

Level: Beginner | Prerequisites: None
Industry: All

This lab introduces the rapidly developing technology of deep learning accelerated by GPUs. The course is intended for anyone looking for a fundamental understanding of deep learning. You will learn:

  • The concept of deep learning
  • How the growth of deep learning has improved machine perception tasks including visual perception, speech recognition, and natural language
  • How to choose which software framework best suits your needs

On completion of this lab, you will have a foundational understanding of accelerated deep learning.

Take the lab


Image Classification with NVIDIA DIGITS

Level: Beginner | Prerequisites: None
Industry: All

This lab shows you how to leverage deep neural networks (DNN) - specifically convolutional neural networks (CNN) - within the deep learning workflow to solve a real-world image classification problem using NVIDIA DIGITS on top of the Caffe framework and the MNIST hand-written digits datasetin this lab, you will learn how to:

  • Architect a Deep Neural Network to run on a GPU
  • Manage the process of data preparation, model definition, model training and troubleshooting
  • Use validation data to test and try different strategies for improving model performance

On completion of this lab, you will be able to use NVIDIA DIGITS to architect, train, evaluate and enhance the accuracy of CNNs on your own image classification application.

Take the lab


Signal Processing Using NVIDIA DIGITS

Level: Beginner | Prerequisites: None
Industry: All

This lab demonstrates how to process data from acoustic, seismic, radio, and radar sensorsin this lab, you will learn how to:

  • Utilize a Convolutional Neural Network (CNN) to process Radio Frequency (RF) signals
  • Detect a weak signal corrupted by noise

On completion of this lab, you will be able to leverage the DIGITS application to read in a dataset, train a CNN, adjust hyper-parameters and then test and evaluate the performance of your model.

Take the lab


Object Detection with NVIDIA DIGITS

Level: Beginner-Intermediate | Prerequisites: Image Classification with NVIDIA DIGITS
Industry: All

This lab introduces students to one of four primary computer vision tasks - object detection - by trying three different approaches: sliding window, fully convolutional network (FCN), and DIGITS’ DetectNet network modelin this lab, you will learn how to:

  • Measure object detection approaches in relation to three metrics: model training time, model accuracy and speed of detection during deployment
  • Implement a sliding window approach to object detection
  • Convert fully connected networks to fully convolutional networks (FCN)
  • Use DIGITS’ DetectNet for more efficient object detection

On completion of this lab, you will understand the merits of each approach and learn how to detect objects using neural networks trained using NVIDIA DIGITS on the Caffe framework on real-world datasets.

Take the lab


Image Segmentation with TensorFlow

Level: Intermediate | Prerequisites: Image Classification with NVIDIA DIGITS
Industry: All

This lab examines the importance of segmenting an image into spatial regions of interest, which goes beyond detecting individual objects within an image. Students learn how to classify pixels of an image instead of entire images. The lab uses the Sunnybrook cardiac MRI dataset to identify the left ventricle of the human heartin this lab, you will learn how to:

  • Use TensorFlow to architect, train and evaluate fully convolutional networks (FCN)
  • Introduce the dice metric to account for class imbalance challenges
  • Adjust hyperparameters to influence training time and model accuracy

On completion of this lab, you will learn how to train and evaluate an image segmentation network with TensorFlow.

Take the lab


Medical Image Segmentation with NVIDIA DIGITS

Level: Beginner | Prerequisites: None
Industry: Healthcare

This lab explores various approaches to the problem of semantic image segmentation, which is a generalization of image classification where class predictions are made at the pixel level. We use the Sunnybrook Cardiac Data to train a neural network to learn to locate the left ventricle on MRI images.
In this lab,you will learn how to:

  • Use popular image classification neural networks for semantic segmentation
  • Extend Caffe with custom Python layers
  • Become familiar with the concept of transfer learning
  • Train two Fully Convolutional Networks (FCNs).

On completion of this lab, you will be able to set up your own image segmentation workflow in DIGITS and adapt it to a medical use case.
Take the lab


Deep Learning for Genomics using DragoNN with Keras and Theano

Level: Beginner | Prerequisites: None
Industry: Healthcare

In this lab, we use the dragonn toolkit on simulated and real regulatory genomic data, demystify popular DragoNN (Deep RegulAtory GenOmics Neural Network) architectures and provide guidelines for modeling and interpreting regulatory sequence using DragoNN models.
In this lab,you will learn how to:

  • Decide when a DragoNN is good choice for a learning problem in genomics
  • Design a high-performance model
  • Interpret these models to discover predictive genome sequence patterns to gain new biological insights

On completion of this lab, you will be able to set up a DragoNN network for genomic research.
Take the lab


Modelling Time Series Data with Recurrent Neural Networks in Keras

Level: Intermediate | Prerequisites: Some experience training CNNs
Industry: Healthcare

One important area of current research is the use of deep neural networks to classify or forecast time-series data. Time-series data is produced in large volumes from sensors in a variety of application domains including Internet of Things (IoT), cyber security, data center management and medical patient care.
In this lab,you will learn how to:

  • Create training and testing datasets using electronic health records in HDF5 (hierarchical data format version five)
  • Design a high-performance model
  • Prepare datasets for use with recurrent neural networks (RNNs), which allows modeling of very complex data sequences

On completion of this lab, you will be able to construct a long-short term memory model (LSTM), a specific RNN architecture, using the Keras library running on top of Theano to evaluate model performance against baseline data.
Take the lab


Medical Image Analysis with R and MXNet

Level: Intermediate | Prerequisites: Image Classification Using NVIDIA DIGITS
Industry: Healthcare

Convolutional neural networks (CNNs) have proven to be just as effective in visual recognition tasks involving non-visible image types as regular RGB camera imagery. One important application of these capabilities is medical image analysis, where we wish to detect features indicative of medical conditions and use them to infer patient status. In addition to processing non-visible imagery, such as CT scans and MRI, these applications often require us to process higher dimensionality imagery that may be volumetric and have a temporal component.
In this lab you will use the deep learning framework MXNet to train a CNN to infer the volume of the left ventricle of the human heart from a time-series of volumetric MRI data.
In this lab,you will learn how to:

  • Extend the canonical 2D CNN to be applied to this more complex data
  • Directly predict the ventricle volume rather than generating an image classification
  • Use MXNet through R, which is an important data science platform in the medical research community

On completion of this lab, you will be able to detect features indicative of medical conditions and use them to infer patient status.
Take the lab


Image Classification with TensorFlow: Radiomics - 1p19q Chromosone Status Classification with Deep Learning

Level: Beginner | Prerequisites: Basic understanding of convolutional neural networks and genomics
Industry: Healthcare

Thanks to work being performed at Mayo Clinic, approaches using deep learning techniques to detect Radiomics from MRI imaging can lead to more effective treatments and yield better health outcomes for patients with brain tumors.
Radiogenomics, specifically Imaging Genomics, refers to the correlation between cancer imaging features and gene expression. Imaging Genomics (Radiomics) can be used to create biomarkers that identify the genomics of a disease without the use of an invasive biopsy.
In this lab,you will learn how to:

  • Detect the 1p19q co-deletion biomarker using deep learning - specifically convolutional neural networks – using Keras and TensorFlow.

On completion of this lab, you will be able to set up your own image segmentation workflow in DIGITS and adapt it to a medical use case.
Take the lab


Linear Classification with TensorFlow

Level: Beginner | Prerequisites: None
Industry: All

Use the TF.Learn API in TensorFlow to solve a binary classification problem: Given census data about a person such as age, gender, education and occupation (the features), we will try to predict whether or not the person earns more than 50,000 dollars a year (the target label). Train a logistic regression model, and given an individual's information our model will output a number between 0 and 1, which can be interpreted as the probability that the individual has an annual income of over 50,000 dollars.
In this lab,you will learn how to:

  • Use Pandas and tf.contrib to load, view, and organize data.
  • Select and engineer data.
  • Train and evaluate a linear model.
  • Use regularization to prevent overfitting.

On completion of this lab, you will be able to go from dataset to trained linear model with multiple datasets.
Take the lab


Neural Network Deployment with NVIDIA DIGITS and TensorRT

Level: Beginner | Prerequisites: Image Classification Using NVIDIA DIGITS
Industry: All

In this lab,you will learn how to:

  • Understand the role of batch size in inference performance
  • Make various optimizations in the inference process.
  • Explore inference for a variety of different DNN architectures trained in other DLI labs.

On completion of this lab, you will be able to execute a full Deep Learning workflow: from loading data, to training a neural network, to deploying that trained network to production.
Take the lab


Deep Learning Workflows with TensorFlow and MXNet and NVIDIA-Docker

Level: Beginner | Prerequisites: Bash terminal familiarity
Industry: All

Docker is a popular container infrastructure which allows programs and large software frameworks to be packaged (i.e. containerized) and distributed as a single pre-configured image – alleviating the need for a complex installation and configuration process on the local host. Together with the nvidia-docker plugin, which exposes the GPU hardware on the host inside of the container, it is possible to run production grade deep learning workflows with considerably reduced host configuration and administration.

In this lab,you will learn how to:

  • Work with Docker images and manage the container lifecycle.
  • Access images on the public Docker image registry DockerHub for maximum reuse in creating composable lightweight containers.
  • Train both TensorFlow and MXNet using nvidia-docker
  • Create your own local registry for hosting Docker images on a private network.

On completion of this lab, you will be able to scale container workflows for the datacenter, understand available tools in the Docker ecosystem and Cloud container services.
Take the lab


Want more? Visit www.nvidia.com/DLI for upcoming DLI workshops, educational deep learning resources, and more.

Join the NVIDIA Developer Program for access to the latest software, tools, and information you need to develop applications using NVIDIA solutions.