$1,524.75 – $3,659.40

Advanced Natural Language Processing and Temporal Sequence Processing

Event Information

Share this event

Date and Time

Location

Location

BASH, Level 3,

79 Ayer Rajah Crescent

139955

Singapore

View Map

Refund Policy

Refund Policy

No Refunds

Event description

Description

Overview

Together with Red Dragon AI, we at SGInnovate are pleased to present the 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 Natural Language Processing (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.

We will also cover some of the most recent developments in using transfer learning for text related problems and language modelling. 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 dialogue systems, in the course you will discover how various types of chatbots work and some of the key technologies behind them and systems like Google's DialogFlow and Duplex.

We will also look at famous applications such as the Neural Machine Translation. You will learn some of the recent developments and models that use such techniques, such as the various types of attention mechanisms that dramatically increase 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 other 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 eligible for funding support. For more details, please refer to the "Pricing" tab above.

In this course, participants will learn:

  • Text Classification Models and build a text classifier
  • To build a Named Entity Recogniser (NER) system
  • About Sequence to Sequence models
  • To build NLP models from scratch
  • To build a Chatbot ML system
  • To build a language model

Mandatory Prerequisites:

  • Attended Module 1: Deep Learning Jump-start Workshop
  • Attendees MUST bring their own laptops


Agenda

Day 1

08:45am – 09:00am: Registration
09:00am – 10:45am: Recurrent Neural Networks Recap Part 1

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

10:45am – 11:00am: Tea Break
11:00am – 12:30pm: Recurrent Neural Networks Recap Part 2
12:30pm – 1:30pm: Lunch
1:30pm – 3:00pm: Natural Language Processing Part 1

  • 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

3:00pm – 3:15pm: Tea Break
3:15pm – 4:45pm: Natural Language Processing Part 2
4:15pm – 5:15pm: Personal Text Project

  • Ideas for projects to do
  • Q&A on ‘doable projects’
  • Homework: What to bring to the next session

5:15pm – 5:30pm: Closing Comments and Questions

Day 2

08:45am – 09:00am: Registration
09:00am – 10:45am:

  • Sequence to Sequence models
  • Convolutions for text networks
  • Clustering
  • Seq2Seq Chatbot

10:45am – 11:00am: Tea Break
11:00am – 12:30pm: Project Clinic 1
Project questions and general follow up

12:30pm – 1:30pm: Lunch
1:30pm – 3:15pm: Time Series

  • Sequence to Sequence models
  • Convolutions for text networks
  • Clustering
  • Seq2Seq Chatbot

2:15pm – 3:30pm: Tea Break
3:30pm – 4:30pm: Project Clinic 2
Project questions and general follow up

4:30pm – 5:00pm: Closing Comments and Questions

Online Content
6 Hours

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


Pricing

This workshop is eligible for CITREP+ funding.

CITREP+ is a programme under the TechSkills Accelerator (TeSA) – an initiative of SkillsFuture, driven by Infocomm Media Development Authority (IMDA).



*Please see below section on ‘Guide for CITREP+ funding eligibility and self-application process’

Funding Amount:

  • CITREP+ covers up to 90% of your nett payable course fee depending on eligibility for professionals

Please note: funding is capped at $3,000 per course application

  • CITREP+ covers up to 100% funding of your nett payable course fee for eligible students/full-time National Service (NSF)

Please note: funding is capped at $2,500 per course application

Funding Eligibility:

  • Singaporean / PR
  • Meets course admission criteria
  • Sponsoring Organisation must be registered or incorporated in Singapore (only for individuals sponsored by organisations)

Please note:

  • Employees of local government agencies and Institutes of Higher Learning (IHLs) will qualify for CITREP+ under the self-sponsored category
  • Sponsoring SMEs organisation who wish to apply for up to 90% funding support for course must meet SME status as defined here

Claim Conditions:

  • Meet the minimum attendance (75%)
  • Complete and pass all assessments and / or projects

Guide for CITREP+ funding eligibility and self-application process:

For more information on CITREP+ eligibility criteria and application procedure, please click here.

In partnership with: Driven by:

For enquiries, please send an email to learning@sginnovate.com


Trainer


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 speciality is in natural language processing and understanding. In 2017, Google appointed Martin as one of the first 12 Google Developer Experts for Machine Learning. Martin is also one of the co-founders of Red Dragon AI.


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. Sam is also one of the co-founders of Red Dragon AI.


Share with friends

Date and Time

Location

BASH, Level 3,

79 Ayer Rajah Crescent

139955

Singapore

View Map

Refund Policy

No Refunds

Save This Event

Event Saved