OVERVIEW
Together with Red Dragon AI, SGInnovate is pleased to present the
third module of the Deep Learning Developer Series. In this module, we
dive deeper into some of the latest techniques for using Deep Learning
for text and time series applications.
In this course, participants will learn about:
* Text classification models and how to build a text classifier
* Constructing a NER system
* Sequence to sequence models
* Building NLP models from scratch
* Creating a chatbot’s Machine Learning system
* Creating a language model
PREREQUISITES:
* Must have attended Module 1: Deep Learning Jump-start Workshop
* Attendees MUST bring their laptops
THIS WORKSHOP IS ELIGIBLE FOR FUNDING SUPPORT. FOR MORE DETAILS,
PLEASE REFER TO THE "PRICING" TAB ABOVE.
MORE ABOUT THIS MODULE:
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 Recurrent Neural Networks (RNNs) and Long
Short-Term Memory (LSTM) are used in NLP.
Another common technique of Deep Learning in NLP is the use of word
and character vector embeddings.
We will cover well-known models such as Word2Vec and GLoVE, how they
are created, their unique properties, and how you can use them to
improve the accuracy of Natural Language in terms of understanding
problems and applications.
Some of the recent developments in using transfer learning for
text-related problems and language modelling, which led to some of the
latest state-of-the-art results for text classification problems like
sentiment analysis, will be highlighted. Papers from ULMFIT, ELMo and
OpenAI’s most recent Transformer model will be covered as well.
One of the most significant applications in Natural Language currently
is the creation of chatbots and dialogue systems. Thus, you will
discover how various types of chatbots work, the primary technologies
behind them, and systems like Google’s DialogFlow and Duplex.
We will also look at applications such as the Neural Machine
Translation. You will learn the recent developments and models that
use these techniques and various types of attention mechanisms that
had dramatically increased the quality of translation systems.
Beyond just text, this module will also cover time-series predictions
and how you can use techniques from the text-based models to make
predictions on sequences. This opens the range of applications to
include financial time-series, continuous IoT readings, machinery
failure prediction, website optimisation and trip planning.
Like the other modules, you will have the opportunity to build
multiple models yourself, giving you the ability to apply these new
skills in your field of work or interest.
ABOUT THE DEEP LEARNING DEVELOPER SERIES:
The Deep Learning Developer Series is a hands-on series targeted at
developers and Data Scientists who are looking to build Artificial
Intelligence (AI) applications for real-world usage. It is an expanded
curriculum that breaks away from the regular eight-week full-time
course structure and allows customisation according to your own pace
and preference.
AGENDA
DAY 1 (13 NOVEMBER 2019)
08:45AM – 09:00AM: Registration
09:00AM – 10:45AM: Recurrent Neural Networks (RNNs) Recap Part 1
* RNNs
* Long Short-Term Memory (LSTM)
* Word embeddings: Word2Vec, GloVE
* Basic Char RNNs
* Word RNNs
* Build LSTM networks
10:45AM – 11:00AM: Tea Break
11:00AM – 12:30PM: RNNs Recap Part 2
12:30PM – 1:30PM: Lunch
1:30PM – 3:00PM: Natural Language Processing (NLP) Part 1
* Text classification models
* Bi-directional LSTMs
* Building a Named Entity Recogniser (NER) system
* Sentiment analysis
* Building a text classifier
* Personal text project
* Major Project Week 1
3:00PM – 3:15PM: Tea Break
3:15PM – 4:45PM: NLP Part 2
4:15PM – 5:15PM: Personal text project
* Ideas on projects to do
* Q&A on ‘doable projects’
* Homework: What to bring to the next session
5:15PM – 5:45PM: Closing comments and questions
DAY 2 (14 NOVEMBER 2019)
08:45AM – 09:00AM: Registration
09:00AM – 10:45AM: Seq2Seq and CNN for Text
* Sequence to sequence models
* Convolutions for text networks
* Clustering
* Seq2Seq Chatbot
10:45AM – 11:00AM: Tea Break
11:00AM – 12:30PM: Project Clinic
_Project questions and general follow up_
12:30PM – 1:30PM: Lunch
1:30PM – 3:15PM: Time Series
* Univariate vs Multivariate/ Stationarity/ TrendsWindowing
* Differencing Arima/ Sarima LSTM for Time Series ConvLSTM for Time
Series
2:15PM – 3:30PM: Tea Break
3:30PM – 4:30PM: The Rise of the Language Models
4:30PM – 5:15PM: Closing comments and questions
PARTICIPANTS WILL BE GIVEN TWO WEEKS TO COMPLETE THEIR ONLINE LEARNING
AND INDIVIDUAL PROJECT.
ONLINE LEARNING
* Building NLP models from scratch
* NLP pipelines
* Guide to using Spacy
* Building a Chatbot Machine Learning system
* Building a language model
PARTICIPANTS MUST FULFIL THE CRITERIA STATED BELOW TO PASS AND
COMPLETE THE COURSE.
1. Online Tests: Participants are required to score an average
grade of more than 75% correct answers to the online questions.
2. Project: Participants are required to present a project that
demonstrates the following:
* The ability to use or create a data processing pipeline that gets
data in the correct format for running in a Deep Learning model
* The ability to create a model from scratch or use transfer
learning to create a Deep Learning model
* The ability to train that model and get results
* The ability to evaluate the model on held out data
PRICING
FUNDING SUPPORT
CITREP+ is a programme under the TechSkills Accelerator (TeSA) – an
initiative of SkillsFuture, driven by Infocomm Media Development
Authority (IMDA).
*Please see the section below 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 Servicemen (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
[https://www.imda.gov.sg/industry-development/programmes-and-grants/individuals/critical-infocomm-technology-resource-programme-citrep]
CLAIM CONDITIONS:
* Meet the minimum attendance (75%)
* Complete and pass all assessments and / or projects
GUIDE FOR CITREP+ FUNDING ELIGIBILITY AND SELF-APPLICATION PROCESS:
* Individuals (Self-Sponsored)
[https://cdn2.hubspot.net/hubfs/3032335/Talent_Workshop-PDF/For_External_Use_CITREP_Funding_Briefing_Slides_self-sponsored_updated_190423.pdf]
* Organisation-Sponsored
[https://cdn2.hubspot.net/hubfs/3032335/Talent_Workshop-PDF/For_External_Use_CITREP_Funding_Briefing_Slides_org-sponsored_updated_190423.pdf]
* Students / NSF
[https://cdn2.hubspot.net/hubfs/3032335/Talent_Workshop-PDF/For_External_Use_CITREP_Funding_Briefing_Slides_students_updated_190423.pdf]
For more information on CITREP+ eligibility criteria and application
procedure, please click here
[https://www.imda.gov.sg/industry-development/programmes-and-grants/individuals/critical-infocomm-technology-resource-programme-citrep].
In partnership with:
Driven by:
In partnership with employers to support employability:
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.
culture
2617
Views
15/11/2019 Last update