The NVIDIA Deep Learning Institute. Hosted by Scan.
Scan Instructor-Led Workshops
Throughout 2019 we will be scheduling our initial course offering and this will rapidly expand into a comprehensive course schedule. For more information see below or click to register your interest:
Register your interestFundamentals of Deep Learning for Multi-GPUs
Prerequisites: Experience with stochastic gradient descent mechanics
Duration: 8 hours
Frameworks: TensorFlow
Languages: English
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.
Fundamentals of Deep Learning for Natural Language Processing
Prerequisites: Basic experience with neural networks and Python programming, familiarity with linguistics
Duration: 8 hours
Frameworks: TensorFlow, Keras
Languages: English, Chinese
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 Accelerated Computing with CUDA Python
Prerequisites: Basic Python competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations. NumPy competency including the use of ndarrays and ufuncs.
Duration: 8 hours
Languages: English
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 Deep Learning for Computer Vision
Prerequisites: Technical background
Duration: 8 hours
Frameworks: Caffee, DIGITS
Languages: English
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
Deep Learning for Digital Content Creation using GANS and Autoencoders
Prerequisites: Technical background
Duration: 8 hours
Frameworks: TensorFlow, Theano, DIGITS
Languages: English
Explore the latest techniques for designing, training, and deploying neural networks for digital content creation. You’ll learn how to:
- Train a Generative Adversarial Network (GAN) to generate images
- Explore the architectural innovations and training techniques used to make arbitrary video style transfer
- Train your own de-noiser for rendered images
Upon completion, you’ll be able to start creating digital assets using deep learning approaches.
Deep Learning for Healthcare Image Analysis
Prerequisites: Fundamentals of Deep Learning for Computer Vision or similar experience
Duration: 8 hours
Frameworks: Caffe, MXNet, TensorFlow
Languages: English
This course explores how to apply Convolutional Neural Networks (CNNs) to MRI scans to perform a variety of medical tasks and calculations. You’ll learn how to:
- Perform image segmentation on MRI images to determine the location of the left ventricle.
- Calculate ejection fractions by measuring differences between diastole and systole using
- CNNs applied to MRI scans to detect heart disease.
- Apply CNNs to MRI scans of LGGs to determine 1p/19q chromosome co-deletion status.
Upon completion, you’ll be able to apply CNNs to MRI scans to conduct a variety of medical tasks.
Deep Learning for Healthcare Genomics
Prerequisites: Fundamentals of Deep Learning for Computer Vision or similar experience
Duration: 8 hours
Frameworks: Caffe, TensorFlow, Theano
Languages: English
This course 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 they work.
- Apply CNNs to MRI scans of 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 Finance Trading Strategy
Prerequisites: Fundamentals of Deep Learning for Computer Vision or similar experience
Duration: 8 hours
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 course, you’ll learn how to:
- Prepare time series data and test network performance using training and test datasets
- Structure and train a 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 Full Motion Video Analytics
Prerequisites: Fundamentals of Deep Learning for Computer Vision or similar experience
Duration: 8 hours
Frameworks: TensorFlow
Languages: English
Traffic cameras, drones, and aerial sensor platforms are collecting huge amounts of video footage, which requires advanced deep learning techniques to transform data into actionable insights. The first step in more complex deep learning workflows is detecting specific types of objects, which involves identification, classification, segmentation, prediction, and recommendation. In this course, you’ll learn how to:
- Train and evaluate deep learning models using the TensorFlow Object Detection API
- Explore the strategies and trade-offs involved in developing high-quality neural network models for track moving objects in large-scale video datasets
- Optimize inference times using TensorRT for real-time applications
Upon completion, you’ll be able to deploy object detection and tracking networks to work on real-time, large-scale video streams.
Deep Learning for Accelerated Computing with CUDA C/C++ competency
Prerequisites: Fundamentals of Deep Learning for Computer Vision or similar experience
Duration: 8 hours
Frameworks: TensorFlow
Languages: English
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
- Utilizing essential CUDA memory management techniques to optimize 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 optimize 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.