Data Science I: NDSC Edition

This course is a specialised version of our Data Science I (Python), designed specifically for the National Data Science Challenge organised by Shopee.

  • TBD
  • 4 sessions
  • 3.5 hours/session
Data Science I: NDSC Edition
$2,000

Price before GST

About this course

About this Course:

This course is a specialised version of our Data Science I (Python), designed specifically for the National Data Science Challenge, organized by Shopee. In this course, students will learn advanced Deep Learning and Natural Language Processing techniques to prepare themselves for the advanced category of this challenge: Product Information Extraction

By the end of the course, students will be able to build advanced Deep Learning structures, namely a "classification" or "prediction" engines for product information extraction. Students will also learn to build Deep Learning models with an aim towards product information extraction. All coding and projects will be done in class, under the supervision of the instructor.

Whether you are thinking of registering or have registered for the National Data Science Challenge, joining this course will definitely give you the head start you need.

Objectives

- Deep learning (DL) models
- DL optimisation techniques
- The overfitting problem and how to solve it
- Structure of Convolutional Neural Networks (CNN)
- Structure of Recurrent Neural Networks (RNN)
- CNN’s top architectures
- Basic natural language processing techniques

Course Plan

1 Fighting overfitting
 1.1 Reducing the network's size
 1.2 Adding weight regularization
 1.3 Adding dropout
1 Understanding recurrent neural networks (RNNs)
 1.1 Our first recurrent layer in Keras
 1.2 A concrete LSTM example in Keras
2 CNN + RNN
 2.1 Creating a dictionary containing all the captions of the images
 2.2 Generator
 2.3 Let's create the model
 2.4 Predict function
1 Lenet-5 (1998)
2 AlexNet (2012)
3 ZFNet(2013)
4 GoogleNet/Inception(2014)
5 VGGNet (2014)
6 ResNet(2015)
7 Inception V3/ V4
8 Assignment: Do some challenge from Kaggle.com
1 Exploring text data using NLTK
 1.1 Counting words
 1.2 Stop words
 1.3 Text normalization
 1.4 n-grams
2 Text classification
 1.1 Binary
 1.2 Multiclass
 1.3 Multilabel
3 Evaluation
 3.1 Precision
 3.2 Recall
 3.3 F1
4 Parts of a speech and meaning
 4.1 Tokenization
 4.2 POS Tagging
 4.3 Chunking and entity recognition

Prerequisites

This course requires a basic understanding of Python. You should either have sat and completed our Python Development Course or already have intermediate-level understanding of Python.

If you have not sat our Python Development course, a Student Affairs Officer will reach out to you upon registration to confirm your mastery of Python.

There are no open runs for this course at the moment. If you're interested in taking this course, you may join the waitlist and you will be notified when there are vacancies.

UpCode Academy

Attend coding classes taught by true experts working in the industry. Get practical instructions and interact with these practitioners during the classes.

  • 23 Courses
  • 1,141 Students
  • 23 Instructors

Subscribe to our Newsletter