Sales Ended

Data Science Meets Deep Learning (Natural Language Processing Module) (13 O...

Event Information

Share this event

Date and Time

Location

Location

Fusionopolis One

Singapore, 138634

Singapore

View Map

Refund Policy

Refund Policy

No Refunds

Event description

Description

1. Start Your Journey toward Data Science

Data Science Meets Deep Learning (NLP Module) is an intermediate level5-week intensive training program. In these 5 week, you will be fully exposed to deep learning and data science both online, offline and with your supportive community, and build up your project portfolio to achieve your career dreams.

All these are brought to you by YiDu AI. Established in 2017, YiDu AI is one of the largest machine learning communities in Singapore. We have brought to you 20+ machine learning seminars and 10 industrial talks. An NUS Enterprise Incubatee, we will keep bringing you the best content, supported by the broader university network.

Co-organizers


屏幕快照 2018-04-06 10.30.20


2. Why This Program

Learn NLP from Experts

Natural Language Processing (NLP) is a key subarea in AI with plenty of applications in robotics, IoT, finance etc..
Strong teaching team composed of industry leaders and excellent senior PhD students - the best set of talents in SG you will probably see.


Fully hands-on

Have the opportunity to work through a real project each week, such as Long-short-term memory (LSTM) for sentiment analysis, word embedding.
The homework is held on Kaggle and get additional practices beyond the classroom hours.


Kaggle Competition with Awards

We are going to hold a Kaggle competition for students in this class. The project is for sentiment analysis, and the instructors and TAs will guide you the journey.
The top 3 winners will be awarded S$500, S$300, S$100 accordingly.


Community

Work with the classmates every weekend in our classroom for your homework and projects with assistance from the TAs.

Join our community with 1000+ Yidu AI members of data scientists, AI researchers and PE/VC investors. ​


Job Referral

Yidu AI has a strong network with many technology companies around Singapore and mainland China.
You can get the referral from us if you wanna join these top tech companies.


3. Curriculum

5 Weekend courses: 1.5 hours teaching + 1.5 hours hands-on in-class project

Hands-on Exercises: We will prepare homework every week which will be posted on Kaggle. Students will have chance to work with Kaggle leaderboard.

Course Project: A final project will be provided as a Kaggle competition for students. The top 3 team will be awarded S$500, S$300, S$100, respectively.

Download the Syllabus Here

Week 1 (13 Oct 9:00am - 12:00pm)

Contents:

  • Basic concepts behind NLP and Deep Learning
  • Representation learning and TF-IDF Models
  • Stochastic gadients descent
  • Softmax and cross entropy error

In-class Project:

Implement a basic Softmax layer from scratch


Week 2 ( 20 Oct, 9:00am - 12:00pm)

Contents:

  1. Non-linearities behind neural networks
  2. Feed-forward computation for NN
  3. Back-propagation for NN
  4. Overfitting, Activation functions, Regularization

In-class Project:

Tutorial on TensorFlow


Week 3 (27 Oct 9:00am - 12:00pm)

Contents:

  1. Count-based Word representation
  2. Neural network-based word2vec
  3. Inherent connections between Word2vec and TF-IDF models
  4. Recurrent Neural Networks and Language Model

In-class Project:

Word vectors training model


Week 4 (3 Nov 9:00am -12:00pm)

Contents:

  1. Language Model
  2. Gradient Vanishing and Exploding
  3. Bi-directional Extension
  4. Cell Extension: LSTM or GRU

In-class Project:

LSTM sentiment analysis


Week 5 (10 Nov 9:00am - 12:00pm)

Contents:

  1. A brief review on CNN
  2. Implement multi-channel CNNs for sentiment analysis
  3. Design the code structure following a standard tensorflow template which can provide a good practice for our daily job.

Details: For sentiment analysis, CNN is able to perform very well due to its compositionality and local invariance. Therefore, in our final projects, we are going to explore CNN on the sentiment analysis tasks.


4. Instructors

Dr. Zhao Rui

Quantitative Researcher in an Asset Management Company, Singapore.

Zhao Rui received his Ph.D degree focusing natural language understanding based on deep learning from NTU in 2017.

After graduation, he worked in Shopee as a Data Scientist involved in several large-scale machine learning projects such as personalized recommendation system, category suggestion and so on.

Mr. Paul Yuan

Founder of YiDu AI. Now PhD student at NUS.

5+ years experience in Optimization Algorithms, Machine Learning and Computer Vision. Co-author of State-Of-the-Art optimization solver.


5. YiDu AI Data Science Community

Started from 2017, Yidu AI has organized tens of industrial talks, machine learning and AI seminar and many other networking events.

Currently, we have a huge community with different channels. We have a Wechat group comprised of 700+ top data scientists and AI researchers in Singapore. Meanwhile, we have a meetup channel with 700+ members.

YiDu AI has an official Wechat account with thousands of followers to post our activities. Please follow us to get more information.

Past Courses & Feedback



Wang He, Software Engineer @Finbook

I took the beginner course. The course gives beginners a solid start with enough real examples and hands-on practice. Besides, the course also provides enough technical and theoretical depth for those with some prior knowledge to explore. Instructors are all experienced industrial data science professionals and PhD students in math/data science. They can explian the things and answer your questions clearly. In general a well designed course. I would highly recommend this course to you!


Yang Zhiyue, Quantitative Analyst

The course covers a broad range of well selected machine learning topics, elaborated by dedicated lecturers and teaching assistants. Together with the theory, interesting and well designed projects are provided. What excited me the most are the course competition on Kaggle and industry talks, from which I benefit significantly. Strongly recommended to those who aim at a data or quant oriented career.


Wang Xiaobai, Software Engineer

The beginner course is a smooth gateway for learner who are not in AI industry or did't not study AI in school.

From basic algorithm to mechine learning thinking, this course write a clear roadmap for who are interest in AI but first time travle in "AI jungle".

I was so excited to training my first model during the course,and it's also a memorable experience to competite with other trainee on Kaggle

Hope you can also join the course and start your AI journey.


Yu Yiming, Senior risk consultant, AIR Worldwide

Yidu AI’s beginner course is very suitable for professionals like me who has already a busy schedule of work. It has a perfect balance of theory and practice. You get to learn and built real life application of ML on day one. The instructors, TA and your classmates are also a big asset of the program. I would highly recommend it to anyone who has enough stats background and is interest in Machine learning and big data.


Xuan, Data Analyst

This is a great short training. I gained practical data science skills through hands-on projects and mathematics teaching. Teachers were passionate PhD student from NUS who are really helpful and detail-driven. The course material was succinct and self-explanatory. The projects were representative. I still review these materials from time to time. I would highly recommend the training to those who hope to have a head start in data science with several weeks.


6. Application

Target Participants

Anyone who is interested in Data Science and Artificial Intelligence.

Pre-requisite: Have basic knowledge of data science: basic mathematical knowledge such as linear algebra and probability, basic programming skills. Background on neural networks will

Check the syllabus of YiDu AI beginner level course.

Application

Please fill out the your basic information in the application form and make the payment. We will come back to you soon.

Timeline: 13th, 20th, 27th Oct, 3rd, 10th Nov. From 9:00AM - 12:00PM.

Location: Fusionopolis

Program fees: S$ 688. We accept at most 35 students for this program. Please register early if you want to attend.

Early Bird Price (first 10 registrants): S$ 599.

Other discount: If you have more than 5 friends who want to attend this program, you could contact us for possible further discount.


7. FAQs

  • Do I need any machine learning /data science background?

Yes. You should be familiar with basic data science and machine learning models. Please check the YiDu AI beginner level course for details. Please contact us if you have any concerns.

  • What do I need to attend this course?

Please bring your own computer and your ID card (for entrance of the classroom).

  • How can I get a refund if I decide not to enroll?

Unfortunately, once enrolled you will not be able to get a refund due to need to cover our cost of venue, instructors, and other logistics. We seek your understanding.

Contact

Email: yiduai.sg@gmail.com

Share with friends

Date and Time

Location

Fusionopolis One

Singapore, 138634

Singapore

View Map

Refund Policy

No Refunds

Save This Event

Event Saved