NVIDIA
Deep Learning Institute

Training You to Solve the World’s Most Challenging Problems

DLI NOW OFFERS DEVELOPER CERTIFICATION IN AI AND ACCELERATED COMPUTING.

The NVIDIA Deep Learning Institute (DLI) offers hands-on training in AI and accelerated computing to solve real-world problems. Designed for developers, data scientists, and researchers, DLI content is available in three formats:

Online
Courses

DLI online courses teach you how to implement and deploy an end-to-end project in eight hours. Online courses can be taken anytime, anywhere, with access to a fully configured GPU-accelerated workstation in the cloud.

Online
ELECTIVES

DLI electives explore how to apply a specific technology or development technique in two hours. Like full-length courses, electives can be taken anytime, anywhere, with access to GPUs in the cloud.

Instructor-Led
Workshops

In-person workshops teach you how to implement and deploy an end-to-end project through hands-on training in eight hours. Offered at customer sites, conferences, and universities, full-day workshops include hands-on training and lectures delivered by DLI certified instructors.

Certification

Certification

Participants can earn certification to prove subject matter competency and support professional career growth. Certification is offered for select online courses and instructor-led workshops.

Online TRAINING

Start self-paced courses and electives anywhere, anytime with access to a fully configured GPU-accelerated workstation in the cloud.

Introduction to Deep Learning

If you’re new to deep learning, the first step is learning how to train and deploy a neural network to solve real-world problems.

COURSES
  • Fundamentals of Deep Learning for Computer Vision 

    Prerequisites: None

    Framework: Caffe

    Languages: English

    Price: $90

    Certification Available

    Explore the fundamentals of deep learning by training neural networks and using results to improve performance and capabilities.

    In this course, you’ll learn the basics of deep learning by training and deploying neural networks. You’ll learn how to:

    • Implement common deep learning workflows, such as image classification and object detection
    • Experiment with data, training parameters, network structure, and other strategies to increase performance and capability
    • Deploy your neural networks to start solving real-world problems

    Upon completion, you’ll be able to start solving problems on your own with deep learning.

ELECTIVES
  • Image Classification with DIGITS

    Prerequisites: None

    Framework: Caffe (with DIGITS interface)

    Languages: English, Chinese, Japanese

    Price: Free

    Deep learning enables entirely new solutions by replacing hand-coded instructions with models learned from examples. Train a deep neural network to recognise handwritten digits by:

    • Loading image data to a training environment
    • Choosing and training a network
    • Testing with new data and iterating to improve performance

    Upon completion, you’ll be able to assess what data you should be using for training.

  • Object Detection with DIGITS

    Prerequisites: Basic experience with neural networks

    Framework: Caffe (with DIGITS interface)

    Languages: English, Chinese

    Price: Free

    Learn to apply deep learning to object detection through the challenge of detecting whale faces from aerial images by:

    • Combining traditional computer vision with deep learning
    • Performing minor “brain surgery” on an existing neural network using the deep learning framework Caffe
    • Harnessing the knowledge of the deep learning community by identifying and using a purpose-built network and end-to-end labeled data

    Upon completion, you’ll be able to solve custom problems with deep learning.

  • Neural Network Deployment with DIGITS and TensorRT

    Prerequisites: Basic experience with neural networks

    Framework: DIGITS, TensorRT

    Languages: English, Chinese

    Price: $30

    Deep learning lets us map inputs to outputs that are extremely computationally intense. Learn to deploy deep learning to applications that recognise images and detect pedestrians in real-time by:

    • Accessing and understanding the files that make up a trained model
    • Building from each function’s unique input and output
    • Optimising the most computationally intense parts of your application for different performance metrics like throughput and latency

    Upon completion, you’ll be able to implement deep learning to solve problems in the real world.

  • Deep Learning Workflows with TensorFlow, MXNet, and NVIDIA Docker

    Prerequisites: Basic experience with a bash terminal

    Framework: TensorFlow, MXNet

    Languages: English, Japanese

    Price: $30

    The NVIDIA Docker plugin makes it possible to containerise production-grade deep learning workflows using GPUs. Learn to reduce host configuration and administration by:

    • Learning to work with Docker images and manage the container lifestyle
    • Accessing images on the public Docker image registry—DockerHub—for maximum reuse in creating composable lightweight containers
    • Training neural networks using both TensorFlow and MXNet frameworks

    Upon completion, you’ll be able to containerise and distribute pre-configured images for deep learning.

  • Image Segmentation with TensorFlow

    Prerequisites: Basic experience with neural networks

    Framework: TensorFlow

    Languages: English

    Price: $30

    Image (or semantic) segmentation is the task of placing each pixel of an image into a specific class. Learn how to segment MRI images to measure parts of the heart by:

    • Comparing image segmentation with other computer vision problems
    • Experimenting with TensorFlow tools such as TensorBoard and the TensorFlow Python API
    • Learning to implement effective metrics for assessing model performance

    Upon completion, you’ll be able to set up most computer vision workflows using deep learning.

  • Image Classification with Microsoft Cognitive Toolkit

    Prerequisites: None

    Framework: Microsoft Cognitive Toolkit

    Languages: English

    Price: $30

    Learn to train a neural network using the Microsoft Cognitive Toolkit framework. You’ll build and train increasingly complex networks to:

    • Compare the expression of a neural network using BrainScript’s “Simple Network Builder” vs. the more generalisable “Network Builder”
    • Visualise neural network graphs
    • Train and test a neural network to classify handwritten digits

    Upon completion, you’ll have basic knowledge of convolutional neural networks (CNNs) and be prepared to move to the more advanced usage of Microsoft Cognitive Toolkit.

  • Linear Classification with TensorFlow

    Prerequisites: None

    Framework: TensorFlow

    Languages: English

    Price: $30

    Learn how to make predictions from structured data using TensorFlow’s TFLearn API. Through the challenge of predicting personal income when given census data, you’ll:

    • Load, view, and organise data from a CSV for machine learning
    • Split an existing dataset into features and labels (input, output) of a neural network
    • Build from linear to deep models and assess the difference in performance

    Upon completion, you’ll be able to make predictions from your own structured data.

  • Signal Processing with DIGITS

    Prerequisites: Basic experience training neural networks

    Framework: Caffe, DIGITS

    Languages: English, Chinese

    Price: $30

    Deep neural networks are better at classifying images than humans, which has implications beyond what we expect of computer vision. Learn how to convert radio frequency (RF) signals into images to detect a weak signal corrupted by noise. You’ll be trained how to:

    • Treat non-image data as image data
    • Implement a deep learning workflow (load, train, test, adjust) in DIGITS
    • Test performance programmatically and guide performance improvements

    Upon completion, you’ll be able to classify both image and image-like data using deep learning.

Introduction to Accelerated Computing

If you’re new to accelerated computing, get started by learning how to accelerate your applications with CUDA and OpenACC.

COURSES
  • Fundamentals of Accelerated Computing with CUDA C/C++ 

    Prerequisites: Basic experience with C/C++

    Languages: English

    Price: $90

    Certification Available

    The CUDA computing platform enables the acceleration of CPU-only applications to run on the world’s fastest massively parallel GPUs. Experience C/C++ application acceleration by:

    • Accelerating CPU-only applications to run their latent parallelism on GPUs
    • Utilising essential CUDA memory management techniques to optimise accelerated applications
    • Exposing accelerated application potential for concurrency and exploiting it with CUDA streams
    • Leveraging command line and visual profiling to guide and check your work

    Upon completion, you’ll be able to accelerate and optimise existing C/C++ CPU-only applications using the most essential CUDA tools and techniques.

  • Fundamentals of Accelerated Computing with CUDA Python

    Prerequisites: Basic experience with Python and NumPy

    Languages: English

    Price: $90

    This course explores how to use Numba—the just-in-time, type-specialising Python function compiler—to accelerate Python programs to run on massively parallel NVIDIA GPUs. You’ll learn how to:

    • Use Numba to compile CUDA kernels from NumPy universal functions (ufuncs)
    • Use Numba to create and launch custom CUDA kernels
    • Apply key GPU memory management techniques

    Upon completion, you’ll be able to use Numba to compile and launch CUDA kernels to accelerate your Python applications on NVIDIA GPUs.

  • Fundamentals of Accelerated Computing with OpenACC

    Prerequisites: Basic experience with C/C++

    Languages: English

    Price: $90

    Learn the basics of OpenACC, a high-level programming language for programming on GPUs. This course is for anyone with some C/C++ experience who is interested in accelerating the performance of their applications beyond the limits of CPU-only programming. In this course, you’ll learn:

    • Four simple steps to accelerating your already existing application with OpenACC
    • How to profile and optimise your OpenACC codebase
    • How to program on multi-GPU systems by combining OpenACC with the message passing interface (MPI)

    Upon completion, you’ll be able to build and optimise accelerated heterogeneous applications on multiple GPU clusters using a combination of OpenACC, CUDA-aware MPI, and NVIDIA profiling tools.

ELECTIVES
  • Accelerating Applications with CUDA C/C++

    Prerequisites: Basic experience with C/C++

    Languages: English, Japanese

    Price: Free

    Learn how to accelerate your C/C++ application using CUDA to harness the massively parallel power of NVIDIA GPUs. You'll learn how to program with CUDA in order to:

    • Accelerate SAXPY algorithms
    • Accelerate Matrix Multiply algorithms
    • Accelerate heat conduction algorithms

    Upon completion, you'll be able to use the CUDA platform to accelerate C/C++ applications.

  • OpenACC – 2X in 4 Steps

    Prerequisites: Basic experience with C/C++

    Languages: English

    Price: Free

    Learn how to accelerate your C/C++ or Fortran application using OpenACC to harness the massively parallel power of NVIDIA GPUs. OpenACC is a directive-based approach to computing where you provide compiler hints to accelerate your code, instead of writing the accelerator code yourself. Get started on the four-step process for accelerating applications using OpenACC:

    • Characterise and profile your application
    • Add compute directives
    • Add directives to optimise data movement
    • Optimise your application using kernel scheduling

    Upon completion, you will be ready to use a profile-driven approach to rapidly accelerate your C/C++ applications using OpenACC directives.

  • Introduction to Accelerated Computing

    Prerequisites: Basic experience with C/C++

    Languages: English

    Price: $30

    Explore the three techniques for accelerating code on a GPU:

    • Using GPU-accelerated libraries
    • Using compiler directives like OpenACC
    • Writing code directly in CUDA-enabled languages

    Upon completion, you'll understand how to demonstrate the potential speed-ups and ease of use of porting to the GPU.

  • GPU Memory Optimisations with CUDA C/C++

    Prerequisites: Accelerating Applications with CUDA C/C++ or similar experience

    Languages: English

    Price: $30

    Explore memory optimisation techniques for programming with CUDA C/C++ on an NVIDIA GPU, and how to use the NVIDIA Visual Profiler (NVVP) to support these optimisations. You'll learn how to:

    • Implement a naive matrix transposing algorithm
    • Perform several cycles of profiling the algorithm with NVVP and optimise its performance

    Upon completion, you'll know how to analyse and improve global and shared memory access patterns, and how to optimise your accelerated C/C++ applications.

  • Accelerating Applications with GPU-Accelerated Libraries in C/C++

    Prerequisites: “Accelerating Applications with CUDA C/C++” or similar experience

    Languages: English

    Price: $30

    Learn how to accelerate your C/C++ application using drop-in libraries to harness the massively parallel power of NVIDIA GPUs. You'll work through three exercises, including how to:

    • Use cuBLAS to accelerate a basic matrix multiply
    • Combine libraries by adding some cuRAND API calls to the previous cuBLAS calls
    • Use nvprof to profile code and optimise with some CUDA Runtime API calls

    Upon completion, you'll be ready to utilise several CUDA enabled libraries for rapid application acceleration in your existing CPU-only C/C++ programs.

  • Accelerating Applications with GPU-Accelerated Libraries in Python

    Prerequisites: Basic experience with Python

    Languages: English

    Price: $30

    Learn how to use GPU libraries to accelerate Python code on NVIDIA GPUs by:

    • Using the cuRAND library to accelerate a Monte Carlo pricer
    • Optimising data movement between the CPU and GPU

    Upon completion, you'll be able to begin using GPU-accelerated Python libraries to accelerate your CPU-only Python code.

  • Using Thrust to Accelerate C++

    Prerequisites: “Accelerating Applications with CUDA C/C++” or similar experience

    Languages: English

    Price: $30

    Thrust is a parallel algorithms library loosely based on the C++ Standard Template Library. It enables developers to quickly embrace the power of parallel computing and supports multiple system back-ends such as OpenMP and Intel's Threading Building Blocks. Use Thrust to accelerate C++ through exercises that cover:

    • Basic Iterators, Containers, and Functions
    • Built-in and Custom Functors
    • Portability to CPU processing

    Upon completion, you'll be ready to harness the power of the Thrust library to accelerate your C/C++ applications.

  • Profiling and Parallelising with OpenACC

    Prerequisites: “OpenACC - 2X in 4 Steps” or similar experience

    Languages: English

    Price: $30

    Get started on the first two steps of the OpenACC programming cycle: identifying parallelism and expressing parallelism. You'll learn how to:

    • Profile a provided C or Fortran application using NVIDIA NVPROF
    • Use the PGI OpenACC compiler to accelerate the code

    Upon completion, you'll be able to profile CPU-only C or Fortran applications to understand where to apply OpenACC directives for application acceleration.

  • Expressing Data Movement and Optimising Loops with OpenACC

    Prerequisites: “Profiling and Parallelising with OpenACC” or similar experience

    Languages: English

    Price: $30

    Learn intermediate OpenACC programming techniques by:

    • Adding OpenACC data management directives
    • Optimising applications using the OpenACC loop directive

    Upon completion, you'll be able optimise data transfers and fine tune application parallelism with OpenACC.

  • Introduction to Multi-GPU Programming with MPI and OpenACC

    Prerequisites: “OpenACC – 2X in 4 Steps” or similar experience

    Languages: English

    Price: $30

    Learn how to program multi-GPU systems or GPU clusters using the Message Passing Interface (MPI) and OpenACC. You'll learn how to:

    • Exchange data between different GPUs using CUDA-aware MPI and OpenACC
    • Handle GPU affinity in multi GPU systems
    • Overlap communication with computation to hide communication times

    Upon completion, you'll be able to accelerate applications with a combination of OpenACC and MPI in multi-GPU environments.

  • Advanced Multi-GPU Programming with MPI and OpenACC

    Prerequisites: “Introduction to Multi-GPU Programming with MPI and OpenACC” or similar experience

    Languages: English

    Price: $30

    Learn how to improve a multi-GPU MPI + OpenACC accelerated applications by:

    • Overlapping communication with computation to hide communication times
    • Handling noncontiguous halo updates with a 2D tiled domain decomposition

    Upon completion, you'll be able to utilise intermediate techniques in applications accelerated with OpenACC and MPI.

  • Pipelining Work on the GPU with OpenACC

    Prerequisites: “Expressing Data Movement and Optimising Loops with OpenACC” or similar experience

    Languages: English

    Price: $30

    Take your OpenACC skills to the next level by optimising data copies to be overlapped with GPU computation using a simple technique known as pipelining. You'll learn how to:

    • Use the OpenACC routine directive to allow on-device function calls
    • Break up large work into bite-sized pieces
    • Work on these pieces asynchronously from the CPU

    Upon completion, you'll be able to use pipelining in OpenACC to make data copies effectively and nearly cost-free.

  • Profile-Driven Approach to Accelerate Seismic Application with OpenACC

    Prerequisites: None

    Languages: English

    Price: $30

    Learn how to use the profiler to improve the experience of accelerating and optimising code for a GPU by:

    • Using the PGI profiler
    • Using the NVIDIA profiler
    • Using OpenACC to accelerate the Kirchhoff 2D Depth Migration included with Seismic Unix

    Upon completion, you'll be able to perform acceleration and data optimisation for several architectures using a profile-driven approach with OpenACC.

  • Accelerating Applications with CUDA Fortran

    Prerequisites: Basic experience with Fortran

    Languages: English

    Price: $30

    Learn how to accelerate your Fortran application using CUDA to harness the massively parallel power of NVIDIA GPUs. You will program with CUDA to:

    • Accelerate SAXPY algorithms
    • Accelerate Matrix Multiply algorithms
    • Accelerate heat conduction algorithms

    Upon completion, you'll be able to use the CUDA platform to accelerate Fortran applications.

  • GPU Memory Optimisations with CUDA Fortran

    Prerequisites: “Accelerating Applications with CUDA Fortran” or similar experience

    Languages: English

    Price: $30

    Learn useful memory optimisation techniques for programming with CUDA Fortran on an NVIDIA GPU, and how to use the NVIDIA Visual Profiler (NVVP) to support these optimisations. You will:

    • Implement a naive matrix transposing algorithm
    • Perform several cycles of profiling the algorithm with NVVP and optimising its performance

    Upon completion, you'll know how to analyse and improve global and shared memory access patterns, and how to optimise your accelerated Fortran applications.

  • Accelerating Applications with GPU-Accelerated Libraries in Fortran

    Prerequisites: Basic experience with Fortran

    Languages: English

    Price: $30

    Discover how to use GPU libraries to accelerate Fortran code on NVIDIA GPUs by:

    • Using the cuRAND library to accelerate a Monte Carlo pricer
    • Optimising data movement between the CPU and GPU

    Upon completion, you'll be able use GPU-accelerated Fortran libraries to accelerate your CPU-only Fortran code.

Deep Learning Training by Industry

Once you have a basic understanding of deep learning, you’ll be able to apply your knowledge to more advanced, industry-specific DLI training to solve real-world problems.

GAME DEVELOPMENT AND DIGITAL CONTENT
 

ELECTIVES
  • Image Creation Using GANs with TensorFlow and DIGITS

    Prerequisites: Experience with CNNs

    Frameworks: TensorFlow

    Languages: English

    Price: $30

    Learn how to train a Generative Adversarial Network (GAN) to generate image contents in DIGITS. You’ll learn how to:

    • Use GANs to create handwritten numbers
    • Visualise the feature space and use attribute vector to generate image analogies
    • Train a GAN to generate images with set attributes

    Upon completion, you’ll be able to use GANs to generate images by manipulating feature space.

  • Image Style Transfer with Torch

    Prerequisites: Experience with CNNs

    Frameworks: Torch

    Languages: English

    Price: $30

    Explore how to transfer the look and feel of one image to another image by extracting distinct visual features. See how convolutional neural networks (CNNs) are used for feature extraction, and how these features feed into a generator to create a new image. You’ll learn how to:

    • Transfer the look and feel of one image to another image by extracting distinct visual features
    • Qualitatively determine whether a style is transferred correctly using different techniques
    • Use architectural innovations and training techniques for arbitrary style transfer

    Upon completion, you’ll be able to use neural networks for arbitrary style transfer at a speed that's effective for video.

  • Rendered Image Denoising Using Autoencoders

    Prerequisites: Experience with CNNs

    Frameworks: TensorFlow

    Languages: English

    Price: $30

    Learn how neural networks with autoencoders can be used to dramatically speed up the removal of noise in ray traced images. You’ll learn how to:

    • Determine whether noise exists in rendered images
    • Use a pre-trained network to denoise some sample images or your own images
    • Train your own denoiser using the provided dataset

    Upon completion, you’ll be able to use autoencoders inside neural networks to train your own rendered image denoiser.

  • Image Super Resolution using AutoEncoders

    Prerequisites: Experience with CNNs

    Frameworks: Keras

    Languages: English

    Price: $30

    Leverage the power of a neural network with autoencoders to create high-quality images from low-quality source images. In this mini course, you'll:

    • Understand and design an autoencoder
    • Learn various methods to rigorously measuring image quality

    Upon completion, you'll be able to use autoencoders inside neural networks to significantly enhance image quality.

HEALTHCARE
 

ELECTIVES
  • Modeling Time Series Data with Recurrent Neural Networks in Keras

    Prerequisites: Basic experience with deep learning

    Frameworks: Keras

    Languages: English

    Price: Free

    Recurrent Neural Networks (RNNs) allow models to classify or forecast time-series data, like natural language, markets, and even a patient’s health over time. You'll learn how to:

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

    Upon completion, you’ll be able to model time-series data using RNNs.

  • Medical Image Classification Using the MedNIST Dataset

    Prerequisites: None

    Frameworks: DIGITS

    Languages: English

    Get a hands-on practical introduction to deep learning for radiology and medical imaging. You'll learn how to:

    • Collect, format, and standardize medical image data
    • Architect and train a convolutional neural network (CNN) on a dataset
    • Use the trained model to classify new medical images

    Upon completion, you’ll be able to apply CNNs to classify images in a medical imaging dataset.

  • Medical Image Segmentation Using DIGITS

    Prerequisites: Basic experience with CNNs and basic experience with Python

    Frameworks: DIGITS, Caffe

    Languages: English

    Price: $30

    Image (or semantic) segmentation is the task of placing each pixel of an image into a specific class. You’ll segment MRI images to measure parts of the heart by:

    • Extending Caffe with custom Python layers
    • Implementing the process of transfer learning
    • Creating fully convolutional neural networks (CNNs) from popular image classification networks

    Upon completion, you’ll be able to set up most computer vision workflows using deep learning.

  • Image Classification with TensorFlow: Radiomics—1p19q Chromosome Status Classification

    Prerequisites: Basic experience with CNNs and basic experience with Python

    Frameworks: TensorFlow

    Languages: English

    Price: $30

    Thanks to work being performed at the Mayo Clinic, using deep learning techniques to detect radiomics from MRI imaging has led to more effective treatments and better health outcomes for patients with brain tumors. Learn to detect the 1p19q co-deletion biomarker by:

    • Designing and training convolutional neural networks (CNNs)
    • Using imaging genomics (radiomics) to create biomarkers that identify the genomics of a disease without the use of an invasive biopsy
    • Exploring the radiogenomics work being done at the Mayo Clinic

    Upon completion, you’ll have unique insight into the novelty and promising results of using deep learning to predict radiomics.

  • Medical Image Analysis with R and MXNet

    Prerequisites: Basic experience with CNNs and basic experience with Python

    Frameworks: MXNet

    Languages: English

    Price: $30

    Convolutional neural networks (CNNs) can be applied to medical image analysis to infer patient status from non-visible images. Learn how to train a CNN to infer the volume of the left ventricle of the human heart from time-series MRI data. You'll explore how to:

    • Extend a canonical 2D CNN to more complex data
    • Use MXNet through the standard Python API and R
    • Process high-dimensionality imagery that may be volumetric and have a temporal component

    Upon completion, you’ll know how to use CNNs for non-visible images.

  • Data Augmentation and Segmentation with Generative Networks for Medical Imaging

    Prerequisites: Experience with CNNs

    Frameworks: TensorFlow

    Languages: English

    Price: $30

    A generative adversarial network (GAN) is a pair of deep neural networks: a generator that creates new examples based on the training data provided and a discriminator that attempts to distinguish between genuine and simulated data. As both networks improve together, the examples created become increasingly realistic. This technology is promising for healthcare, because it can augment smaller datasets for training of traditional networks. You'll learn how to:

    • Generate synthetic brain MRIs
    • Apply GANs for segmentation
    • Use GANs for data augmentation to improve accuracy

    Upon completion, you'll be able to apply GANs to medical imaging use cases.

  • Coarse-to-Fine Contextual Memory for Medical Imaging

    Prerequisites: Experience with CNNs

    Frameworks: TensorFlow

    Languages: English

    Price: $30

    Coarse-to-fine contextual memory (CFCM) is a technique developed for image segmentation using very deep architectures and incorporating features from many different scales with convolutional long short-term memory (LSTM). You’ll:

    • Take a deep dive into encoder-decoder architectures for medical image segmentation
    • Get to know common building blocks (convolutions, pooling layers, residual nets, etc.)
    • Investigate different strategies for skip connections

    Upon completion, you'll be able to apply CFCM techniques to medical image segmentation and similar imaging tasks.

  • Deep Learning for Genomics Using DragoNN with Keras and Theano

    Prerequisites: Basic experience with convolutional neural networks (CNNs) and basic experience with Python

    Frameworks: Keras, Theano

    Languages: English

    Price: $30

    Learn to interpret deep learning models to discover predictive genome sequence patterns. Use the deep regulatory genomics neural network (DragoNN) toolkit on simulated and real regulatory genomic data to:

    • Demystify popular DragoNN architectures
    • Explore guidelines for modeling and interpreting regulatory sequence using DragoNN models
    • Identify when DragoNN is a good choice for a learning problem in genomics and high-performance models

    Upon completion, you’ll be able to use the discovery of predictive genome sequence patterns to gain new biological insights.

INTELLIGENT VIDEO ANALYTICS
 

ELECTIVES
  • Deployment for Intelligent Video Analytics using TensorRT

    Prerequisites: Basic experience with CNNs and C++

    Frameworks:TensorRT

    Languages: English

    Price: $30

    When a trained neural network is tasked to find the answer on new data inputs, it is referred to as deployment. TensorRT is the primary tool for deployment, with various options to improve inference performance of neural networks. In this mini course, you'll:

    • Learn how to use giexec to run inferencing.
    • Use mixed precision INT8 to optimize inferencing.
    • Leverage custom layers API for plugins.

    Upon completion, you'll know how to use TensorRT to accelerate inferencing performance for neural networks.

Instructor-Led Workshops

Find an upcoming workshop near you or request a workshop onsite.

Attend Upcoming Workshops.

FREE WORKSHOPS FOR ACADEMIA

These workshops are free and exclusive for verifiable academic students, staff and researchers.

Bring DLI to Your Organisation.

Managers can request onsite DLI workshops at their company or organisation. Choose from fundamentals or industry-specific topics listed below.

If you’re looking for more comprehensive enterprise training, we’ll work with you to craft a package of training and lectures that meets your organisation’s unique needs. From hands-on online and onsite training to executive briefings and enterprise-level reporting, DLI can help your company transform into an AI organisation. Contact us to learn more.

INTRODUCTION TO DEEP LEARNING

  • Fundamentals of Deep Learning for Computer Vision 

    Prerequisites: None

    Frameworks: Caffe

    Languages: English

    Certification Available

    Explore the fundamentals of deep learning by training neural networks and using results to improve performance and capabilities.

    In this workshop, you’ll learn the basics of deep learning by training and deploying neural networks. You’ll learn how to:

    • Implement common deep learning workflows, such as image classification and object detection
    • Experiment with data, training parameters, network structure, and other strategies to increase performance and capability
    • Deploy your neural networks to start solving real-world problems

    Upon completion, you’ll be able to start solving problems on your own with deep learning.

  • Fundamentals of Deep Learning for Multiple Data Types

    Prerequisites: “Fundamentals of Deep Learning for Computer Vision” or similar experience

    Frameworks: TensorFlow

    Languages: English

    This workshop explores how convolutional and recurrent neural networks can be combined to generate effective descriptions of content within images and video clips.

    Learn how to train a network using TensorFlow and the Microsoft Common Objects in Context (COCO) dataset to generate captions from images and video by:

    • Implementing deep learning workflows like image segmentation and text generation
    • Comparing and contrasting data types, workflows, and frameworks
    • Combining computer vision and natural language processing

    Upon completion, you’ll be able to solve deep learning problems that require multiple types of data inputs.

  • Fundamentals of Deep Learning for Natural Language Processing 

    Prerequisites: Basic experience with neural networks

    Frameworks: TensorFlow, Keras

    Languages: English

    Certification Available

    Learn the latest deep learning techniques to understand textual input using natural language processing (NLP). You’ll learn how to:

    • Convert text to machine-understandable representations and classical approaches
    • Implement distributed representations (embeddings) and understand their properties
    • Train machine translators from one language to another

    Upon completion, you’ll be proficient in NLP using embeddings in similar applications.

  • Fundamentals of Deep Learning for Multi-GPUs 

    Prerequisites: Experience with stochastic gradient descent mechanics

    Frameworks: TensorFlow

    Languages: English

    Certification Available

    The computational requirements of deep neural networks used to enable AI applications like self-driving cars are enormous. A single training cycle can take weeks on a single GPU or even years for larger datasets like those used in self-driving car research. Using multiple GPUs for deep learning can significantly shorten the time required to train lots of data, making solving complex problems with deep learning feasible.

    This workshop will teach you how to use multiple GPUs to train neural networks. You'll learn:

    • Approaches to multi-GPUs training
    • Algorithmic and engineering challenges to large-scale training
    • Key techniques used to overcome the challenges mentioned above

    Upon completion, you'll be able to effectively parallelize training of deep neural networks using TensorFlow.

INTRODUCTION TO ACCELERATED COMPUTING

  • Fundamentals of Accelerated Computing with CUDA C/C++ 

    Prerequisites: Basic experience with C/C++

    Languages: English

    Certification Available

    The CUDA computing platform enables the acceleration of CPU-only applications to run on the world’s fastest massively parallel GPUs. Experience C/C++ application acceleration by:

    • Accelerating CPU-only applications to run their latent parallelism on GPUs
    • Utilising essential CUDA memory management techniques to optimise accelerated applications
    • Exposing accelerated application potential for concurrency and exploiting it with CUDA streams
    • Leveraging command line and visual profiling to guide and check your work

    Upon completion, you’ll be able to accelerate and optimise existing C/C++ CPU-only applications using the most essential CUDA tools and techniques. You’ll understand an iterative style of CUDA development that will allow you to ship accelerated applications fast.

DEEP LEARNING WORKSHOP BY INDUSTRY

  • Deep Learning for Autonomous Vehicles—Perception

    Prerequisites: Experience with CNNs

    Frameworks: TensorFlow, DIGITS, TensorRT

    Languages: English

    In this workshop, you’ll learn how to design, train, and deploy deep neural networks for autonomous vehicles using the NVIDIA DRIVE PX development platform.

    Learn how to:

    • Integrate sensor input using the DriveWorks software stack
    • Train a semantic segmentation neural network
    • Optimise, validate, and deploy a trained neural network using TensorRT

    Upon completion, students will be able to create and optimise perception components for autonomous vehicles using NVIDIA DRIVE PX.

  • Deep Learning for Finance Trading Strategy

    Prerequisites: Experience with neural networks and knowledge of financial industry

    Frameworks: TensorFlow

    Languages: English

    Linear techniques like principal component analysis (PCA) are the workhorses of creating “eigenportfolios” for use in statistical arbitrage strategies. Other techniques using time series financial data are also prevalent. But now, trading strategies can be advanced with the power of deep neural networks.

    In this workshop, you’ll learn how to:

    • Prepare time series data and test network performance using training and test datasets
    • Structure and train a long short-term memory (LSTM) network to accept vector inputs and make predictions
    • Use the autoencoder as anomaly detector to create an arbitrage strategy

    Upon completion, you’ll be able to use time series financial data to make predictions and exploit arbitrage using neural networks.

  • Deep Learning for Digital Content Creation Using Autoencoders

    Prerequisites: Experience with CNNs

    Frameworks: Torch, TensorFlow

    Languages: English

    Certification Available

    Explore the latest techniques for designing, training, and deploying neural networks for digital content creation. You’ll learn how to:

    • Apply the architectural innovations and training techniques used to make arbitrary video style transfer
    • Train your own denoiser for rendered images
    • Upscale images with super resolution AI

    Upon completion, you’ll be able to start creating digital assets using deep learning approaches.

  • Deep Learning for Healthcare Image Analysis

    Prerequisites: Basic experience with CNNs and Python

    Frameworks: Caffe, DIGITS, MXNet, TensorFlow

    Languages: English

    Certification Available

    This workshop teaches you how to apply deep learning to detect chromosome co-deletion and search for motifs in genomic sequences. You’ll learn how to:

    • Understand the basics of convolutional neural networks (CNNs) and how they work
    • Apply CNNs to MRI scans of low-grade gliomas (LGGs) to determine 1p/19q chromosome co-deletion status
    • Use the DragoNN toolkit to simulate genomic data and to search for motifs

    Upon completion, you’ll be able to: understand how CNNs work, evaluate MRI images using CNNs, and use real regulatory genomic data to research new motifs.

  • Deep Learning for Healthcare Genomics

    Prerequisites: Basic experience with CNNs and Python

    Frameworks: Caffe, TensorFlow, Theano

    Languages: English

    Certification Available

    This workshop teaches you how to apply deep learning to detect chromosome co-deletion and search for motifs in genomic sequences. You’ll learn how to:

    • Understand the basics of convolutional neural networks (CNNs) and how they work
    • Apply CNNs to MRI scans of low-grade gliomas (LGGs) to determine 1p/19q chromosome co-deletion status
    • Use the DragoNN toolkit to simulate genomic data and to search for motifs

    Upon completion, you’ll be able to: understand how CNNs work, evaluate MRI images using CNNs, and use real regulatory genomic data to research new motifs.

University Ambassador Program

Qualified educators can teach DLI workshops on their university campus to faculty, students, and researchers at no cost.

Join DLI University Ambassadors from prestigious universities around the world. Plus, download NVIDIA Teaching Kits for lecture materials, hands-on courses, GPU cloud resources, and more.

Participating Universities

Arizona State University
Columbia
The Hong Kong University Of Science And Technology