Fundamentals of Deep Learning for Natural Language Processing
Presented by SGInnovate, NVIDIA & NSCC
SGInnovate, together with the NVIDIA Deep Learning Institute (DLI) is proud to bring to you Fundamentals of Deep Learning for Natural Language Processing.
Led by experienced instructors, you can expect to learn the latest deep learning techniques for designing and deploying neural network-powered machine learning across a variety of application domains.
In the course, participants will learn to:
- Implement common deep learning workflows such as image segmentation and text generation
- Compare and contrast data types, workflows, and frameworks
- Combine deep learning powered computer vision and natural language processing to start
- Solve sophisticated real-world problems that require multiple input data types
This workshop teaches you to apply deep learning techniques for understanding textual input using Natural Language Processing (NLP) through a series of hands-on exercises. You will work with widely-used deep learning tools, frameworks, and workflows by performing neural network training on a fully-configured GPU accelerated workstation in the cloud.
The course starts with the technique of training a neural network for text classification followed by building a linguistic style model to extract features from a given text document and concludes with a neural machine translation model for translating one language to another.
You should also have basic experience with Neural Networks and python programming and/or familiarity with linguistics.
08:45am – 09:00am: Registration
09:00am – 09:45am: Introduction
Introduction to deep learning, situations in which it is useful, key terminology, industry trends and challenges
- Course Overview
- Getting Started with Deep Learning
09:45am – 10:00am: Tea Break
10:00am – 12:00pm: Image Segmentation with TensorFlow
Hands-on exercise: Segment MRI images to measure parts of the heart using tools such as TensorBoard and the TensorFlow Python API
- Compare image segmentation to other computer vision problems
- Experiment with TensorFlow tools
- Implement effective metrics for assessing model performance
12:00pm – 1:00pm: Lunch
1:00pm – 3:00pm: Word Generation with TensorFlow
Hands-on exercise: Train a Recurrent Neural Network to understand both images and text, and to predict the next word of a sentence using the MSCOCO (Microsoft Common Objects in Context) dataset
- Introduction to Natural Language Processing (NLP) and Recurrent Neural Networks (RNNs)
- Create network inputs from text data
- Test with new data
- Iterate to improve performance
3:00pm – 3:15pm: Tea Break
3:15pm – 5:15pm: Image and Video Captioning
Hands-on exercise: Train a model that generates a description of an image from raw pixel data by combining outputs of multiple networks (CNNs and RNNs) through concatenation and/or averaging.
- Combine computer vision and natural language processing to describe scenes
- Learn to harness the functionality of Convolutional Neural Networks (CNNs) and RNNs
5:15pm – 5:30pm: Summary
Review of concepts and practical takeaways
- Summary of key learnings
- Workshop survey
For group discounts or enquiries, please contact [email protected].
You may also like the following:
AI Roundtable: Corporate-Startup Collaboration
Artificial Intelligence (AI) is on the rise, and very rapidly so. This technology for next-generation intelligence and decision making is permeating every industry and much of human activity. AI technology is also getting more advanced increasingly fast, creating more and more possibilities and opportunities.Topics:
Canada’s Perspectives on Advanced Vehicle and Industry Technology
Global industries and governments are racing to bring self-driving vehicles to their streets and – just as importantly – competing to make the greatest strides to capture that market. The 2018 KPMG Autonomous Vehicles Readiness Index (AVRI), which rates major industrial countries on their ability to adopt self-driving vehicles en masse, ranked Canada seventh in overall readiness for a world of self-driving vehicles. Canada’s advantages for developing autonomous technology include a highly skilled workforce and leading work in artificial intelligence.Topics:
The Future of Finance: How FinTech Initiatives Are Driving Innovation in Financial Services
The financial sector has been making bold bets on the digital revolution. For this event, we bring together the brightest and best fintech professionals from universities and the industry for an afternoon of thoughtful discussions, knowledge sharing, and networking. This session will cover both technical updates and market trends. Come join us and stay ahead of the competition!Topics:
Holland Innovation Seminar: Exploring collaboration opportunities in the field of Artificial Intelligence
Singapore and the Netherlands are both ranked in the top five of the most innovative economies in the world on the Global Innovation Index. Both countries attach great importance to innovation and the triple helix approach, bringing government, academics and industry together to collaborate. How can we deepen and expand our R&D efforts, especially in the field of AI?Topics:
Artificial intelligence is already a part of our everyday lives, but for it to truly make a difference it needs to understand human emotions, says Live with AI founder Pierre Robinet.
This article is written by Pierre Robinet, who is a senior consulting partner at Ogilvy Consulting and founder of Live With AI, an independent think tank based in Singapore.