Advanced Natural Language Processing and Temporal Sequence Processing | SGInnovate
November 22-23
2018

Location

Perl @ BASH, Level 3
79 Ayer Rajah Cresent
Singapore 139955

Price

Normal Ticket (Ticket Inclusive of G.S.T) - $1605

Advanced Natural Language Processing and Temporal Sequence Processing

Presented by Red Dragon AI. Partnered with SGInnovate

SGInnovate partners with Red Dragon AI to introduce to you - Deep Learning Developer Series. This workshop is the third installation of the Deep Learning Series Workshop. In this module we go much deeper into some of the latest techniques for using Deep Learning for text and time series applications.

One of the core skills in NLP is reliably detecting entities and classifying individual words according to their parts of speech.  We will look at how Named Entity Recognition (NER) works and how RNNs and LSTMs are used for tasks like this and many others in NLP.

Another common technique of Deep Learning in NLP is the use of word and character vector embeddings.  We will cover such famous models as Word2Vec and GLoVE, how these are created, some of their unique properties and how you can use them to improve the accuracy of natural langue understanding problems and applications.

Start here

    • Have an interest in Deep Learning?
    • Join us if you are able to read and follow codes
    • This module is compulsory before you take the advanced modules
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 AND module 2 OR 3 before this module
     
    • You will need to take module 1, 2 AND 3 before this module
    • Attain a “Deep Learning Specialist” certification when you complete all five modules
     
    • Have an interest in Deep Learning?
    • Join us if you are able to read and follow codes
    • This module is compulsory before you take the advanced modules
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 AND module 2 OR 3 before this module
     
    • You will need to take module 1, 2 AND 3 before this module
    • Attain a “Deep Learning Specialist” certification when you complete all five modules
     

We will also cover some of the most recent developments in using transfer learning for text related problems and language modeling.  These are leading to some of the most recent state of the art results for text classification problems like sentiment analysis and many more.  This section will cover the papers ULMFIT , ELMo and OpenAI’s most recent Transformer model.

As one of the biggest applications in natural language currently is the creation of chatbots and dialog systems, in the course you will discover how various types of chatbots work and some of the key technology behind them and systems like Google’s DialogFlow and Duplex.

We will also look at such famous application as Neural Machine Translation.  You will learn some of the recent developments and models that use such techniques such as various types of attention mechanisms that dramatically increased the quality of translation systems.

Beyond text, this course will also cover time series predictions and how you can use techniques from the text-based models to make predictions on sequences.  This opens up the range of applications to include financial time-series; continuous IoT readings; machinery failure prediction; website optimisation and trip planning.

Building on the tools taught in the first module, we will be going beyond just using TensorFlow and Keras, to introduce PyTorch and TorchText, which are often used for research because of their flexibility in creating cutting edge architectures.

As with all the Deep Learning Developer modules you will have the opportunity to build multiple models yourself including your main project - giving you the ability to take these newly learned skills and apply them to an application that relates to your field of work or general interest.

Overall this course allows you to get an understanding of what can be done in cutting-edge NLP and time series prediction, and how these techniques can be applied - so that you can use these skills in your job. 

This workshop is pending funding approval. More details to be released soon. Please leave your contact details so that we can contact you the moment workshop is open for registration.


The workshop will be held over 2 intensive days coupled with 6 hours’ worth of online content. This allows you to quickly learn the skills needed to apply Deep Learning and have access to ask your questions one on one. This is especially useful for understanding how to apply these skills to your unique applications.

Prerequisites:
Attended Module 1: Deep Learning Jump-start Workshop (Please embed workshop link)

Attendees MUST bring their own laptops

Agenda:

Day 1
Title: Recurrent Neural Networks Recap 
Topics Covered:

  • Recurrent Neural Networks
  • LSTMs (Long Short Term Memory)
  • Word Embeddings: Word2Vec, GloVE
  • Basic Char RNN
  • Word RNN
  • Build LSTM networks

Title: Natural Language Processing
Topics covered:

  • Text Classification Models
  • BiDirectional LSTMs
  • Building a Named Entity Recogniser (NER) system
  • Sentiment analysis
  • Build a text classifier
  • Personal Text project
  • Major Project Week 1

 

Day 2
Title: A
Topics Covered:

  • Sequence to Sequence models
  • Convolutions for text networks
  • Clustering
  • Seq2Seq Chatbot
  • Major Project week 2

Title: Time Series 
Topics Covered:

  • Dealing with date times in models
  • Time Series models

Online Content
Title: Video Walk throughs
Duration: 6 hrs
Topics Covered:

  • Building NLP models from scratch
  • NLP piplines
  • Guide to using Spacy
  • Building a Chatbot ML System
  • Building a language model

 

Instructors’ Biodata:
Dr Martin Andrews
Martin has over 20 years’ experience in Machine Learning and has used it to solve problems in financial modelling and has created AI automation for companies. His current area of focus and specialty is in natural language processing and understanding. In 2017, Google appointed Martin as one of the first 12 Google Developer Experts for Machine Learning.

Sam Witteveen
Sam has used Machine Learning and Deep Learning in building multiple tech start-ups, including a children’s educational app provider which has over 4 million users worldwide. His current focus is AI for conversational agents to allow humans to interact easier and faster with computers. In 2017, Google appointed Sam as one of the first 12 Google Developer Experts for Machine Learning in the world.
 

Topics: Artificial Intelligence / Deep Learning / Machine Learning / Robotics

You may also like the following:

  • Deep Learning Jump-Start Workshop

    SGInnovate partners with Red Dragon AI to introduce to you - Deep Learning Developer Series. Back by popular demand, the Deep Learning Jump-start workshop is the first module of the Deep Learning Developer Series. This 2-days packed workshop is designed to introduce you to the skills needed to start your journey as a Deep Learning Developer. By the end of the workshop, expect to be empowered with the ability to take your new-found Deep Learning knowledge and apply it in your job/projects straight away!

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • Quantum Tech: From Science to Business Applications

    How is quantum technology going to change our daily life? Can quantum computers predict our future? What are the possible business applications and how do we prepare for them starting today? We’ll take a deep look into technology – moving from theory to practical implementation

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics, Blockchain, Data Science / Data Analytics

  • What Can We Expect from Machine Cognition

    Recent decades have witnessed the remarkable progress in artificial intelligence (AI). However, there are still opposing views on the prospect of AI as being yet another cyclic hype or a new development with sustaining power. As the evidence becomes less controversial in the area of recognition, we focus the discussion on the next level of mental capacity necessary to intelligent behaviors, namely, the capability of cognition that involves knowledge acquisition, inference and reasoning, and reinforcement learning. We present our views by way of the current status of Microsoft Academic Graph (MAG), a project in Microsoft Research that teaches machine to obtain knowledge by reading scholarly publications, and contemplate what machine can do in the near future based on the trajectory being observed thus far. As MAG is open to the public, how it can be used through PySpark and what types of applications it has enabled will also be described.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • Appier Masterclass: Creativity in AI

    At the second Appier AI Masterclass, Dr Min Sun, Chief AI Scientist at Appier, will discuss the current capabilities and future potential of Artificial Intelligence to generate creative outputs. Dr Sun will share the research trends in this direction and what his extensive research has uncovered. Finally, he will show how he applies this knowledge at Appier, and how to effectively use AI and deep learning in the creative process. 

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics, Data Science / Data Analytics

  • Future Economy: AI and the Future of Work

    The future of work is increasingly becoming a reality with Artificial Intelligence (AI) set to deliver step changes in productivity last witnessed with mass production in the 1920s – only this time across multiple industries and sectors. 

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics, Data Science / Data Analytics

  • Jump-start Alumni Gathering

    Calling all our Jump-start alumni as we come together to explore and talk about the current state-of-the-art technologies in Deep Learning. Building upon the foundational knowledge in module one, Dr Martin and Sam will teach and touch on advanced deep learning in Computer Vision and advanced Natural Language Processing, Text and Sequences. 

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics