This workshop series will be conducted over three days via NVIDIA’s DLI virtual classroom environment using an online training platform that leverages supercomputing resources in the cloud.
Day 1: Fundamentals of Deep Learning for Computer Vision
This workshop teaches deep learning techniques for a range of computer vision tasks. After an introduction to deep learning, students advance to building and deploying deep learning applications for image classification and object detection, modifying your neural networks to improve their accuracy and performance, and implementing the techniques they’ve learned on a final project. At the end of this module, students have access to additional resources to create new deep learning applications on your own.
Topics:
- Join the account at courses.nvidia.com/join
- Learn the biological inspiration behind deep neural networks (DNNs).
- Explore training DNNs with big data.
- Train neural networks to perform image classification by harnessing the three main ingredients of deep learning: deep neural networks, big data, and the GPU.
- Deploy trained neural networks from their training environment into real applications.
- Optimize DNN performance.
- Incorporate object detection into your DNNs.
- Validate learnings by applying the deep learning application development workflow (load dataset, train, and deploy model) to a project.
- Learn how to set up your GPU-enabled environment to begin work on your own projects.
- Explore additional project ideas and resources to get started with NVIDIA AMI in the cloud, nvidia-docker, and the NVIDIA DIGITS container.
*Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Day 2: Fundamentals of Deep Learning for Multiple Data Types
This workshop uses a series of hands-on exercises to teach deep learning techniques for a range of problems involving multiple data types. Students advance to building deep learning applications for image segmentation, sentence generation, and image and video captioning, while learning relevant computer vision, neural network, and natural language processing concepts. At the end of this workshop, students will be able to assess a broad spectrum of problems where deep learning can be applied. The tools that are used TensorFlow and TensorBoard.
Topics:
- Join the account at courses.nvidia.com/join
- Compare image segmentation to other computer vision problems.
- Experiment with TensorFlow tools.
- Implement effective metrics for assessing model performance.
- Learn about natural language processing (NLP) and recurrent neural networks (RNNs).
- Create network inputs from text data.
- Test with new data and iterate to improve performance.
- Combine computer vision and natural language processing to describe scenes.
- Learn to harness the functionality of convolutional neural networks (CNNs) and RNNs.
*Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Day 3: Fundamentals of Deep Learning for Natural Language Processing
This workshop teaches deep learning techniques for understanding textual input using natural language processing (NLP) through a series of hands-on exercises. Students will learn techniques to train a neural network for text classification, build a linguistic style model to extract features from a given text document, and create a neural machine translation model for converting text from one language to another. The tools used are TensorFlow and Keras.
Topics:
- Join the account at courses.nvidia.com/join
- Explore the importance of data representation for computers to understand language, as well as NLP challenges and how to tackle them with deep learning.
- Learn about distributed data representations, such as word embeddings, using the Word2Vec algorithm. Once trained, word embeddings can be used for text classification.
- Build a linguistic style model to extract features from a given set of texts using embeddings.
- Use text classification to determine the authors of an unknown set of documents.
- Create a neural machine translation model to convert text from one language to another.
- Learn the basic technique to translate human-readable text to machine- readable format.
- Use attention mechanisms to improve results—especially for long strings.
*Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.