Call +60 3-7490 2093 Email:

HRDF Approved Training Provider in Malaysia - Modular Fast Track Skill-Based Trainings

5 Days Machine Learning Specialization

This Machine Learning Specialization  introduces you to the exciting, high-demand field of Machine Learning. Through a series of hand on practical exercises, you will gain applied experience in major areas of Machine Learning including Prediction, Classification, Clustering, Computer Vision and Deep Learning. You will learn to analyze data and  build intelligent applications that can make predictions from data.

This five days classroom facilitator Machine Learning Specialisation course will build your fundation in Python first, then follow by classical Machine Learning using Scikit Learn, follow by Deep Learning using Tensorflow 2.x framework.

Course Highlights

  • Python Programming
  • Classifcation Algorithmes
  • Regression Algorithms 
  • Clustering Algorithsms
  • Predictive Modeling with Neural Network 
  • Image Classification with Convolutional Neutral Network and Deep Learning 
  • Transfer Leanring with Pretrained Models
  • Sentimental Analysis using Recurrent NN


All participants will receive a Certificate of Completion from Tertiary Courses after achieved at least 75% attendance.

HRDF SBL Claimable for Employers Registered with HRDF

HRDF claimable

Course Code: M1050

Course Booking


Course Date

Course Time

* Required Fields

Course Cancellation/Reschedule Policy

We reserve the right to cancel or re-schedule the course due to unforeseen circumstances. If the course is cancelled, we will refund 100% to participants.
Note the venue of the training is subject to changes due to class size and availability of the classroom.
Note the minimal class size to start a class is 3 Pax.

Course Details

Day 1
Module 1 Basic Python

Topic 1.1 Get Started with Python

  • Overview
  • Install Python
  • Install Sublime Text & PyCharm
  • First Python Script
  • Comment

Topic 1.2 Data Types

  • Number 
  • String 
  • List
  • Tuple
  • Dictionary
  • Set

Topic 1.3 Operators

  • Arithmetic Operators
  • Compound Operators
  • Comparison Operators
  • Membership Operators
  • Logical Operators
  • Identity Operators

Topic 1.4 Control Structure

  • Conditional
  • Loop
  • Iterating Over Multiple Sequences
  • Break & Continue
  • Loop with Else

Topic 1.5 Function

  • Function Syntax
  • Return Single Value
  • Return Multiple Values
  • Passing Arguments
  • Default Arguments
  • Variable Arguments
  • Decorator
  • Lambda, Map, Filter

Topic 1.6 Modules & Packages

  • Modules
  • Packages
  • Python Standard Libraries
  • Install Third Party Packages
  • Anaconda Packages

Day 2
Module 2 Advanced Python

Topic 2.1 Comprehensions & Generators

  • Comprehension Syntax
  • Types of Comprehension
  • Generator Syntax
  • Types of Generators

Topic 2.2 File and Directory Handling

  • Read and Write Data to Files
  • Manage File and Folders with Python OS Module
  • Manage Paths with Python Pathlib Module

Topic 2.3 Object Oriented Programming

  • Introduction to Object Oriented Programming
  • Create Class and Objects
  • Method and Overloading
  • Initializer & Destructor
  • Inheritance
  • Polymorphism

Topic 2.4 Database

  • Setup SQLite3 database
  • Apply CRUD operations on SQLite3
  • Integrate to external databases

Topic 2.5 Error Handling Using Exception

  • Exceptions versus Syntax Errors
  • Handle Exceptions with Try and Except blocks
  • The Else clause
  • Clean up with Finally

Topic 2.6 Intro to Useful Packages

  • Numpy
  • Matplotlib
  • Pandas

Day 3
Module 3 Machine Learning with Scikit Learn

Topic 3.1 Getting Started on Scikit-Learn

  • What is Scikit Learn
  • Scikit Learn Applications
  • Installing Scikit-Learn

Topic 3.2 Classification

  • What is Classification
  • Classifier Algorithms
  • Classification Steps
  • Ensemble Classifiers
  • Save and Load Models
  • Confusion Matrix
  • Classification Metrics - Precision, Recall, F1 Score

Topic 3.3 Regression

  • What is Regression
  • Regression Algorithms
  • Linear Regression
  • Multivariate Regression

Topic 3.4 Clustering

  • What is Clustering
  • Clustering Algorithms

Topic 3.5 Dimension Reduction

  • Principal Component Analysis

Day 4
Module 4 Basic Neural Network with Tensorflow

Topic 4.1 Overview of Machine Learning & Tensorflow

  • Overview of Machine Learning and Deep Learning
  • Introduction to Tensorflow 2.x
  • Install Tensorflow 2.x

Topic 4.2 Basic Tensorflow Operations

  • Basic Tensor Data Types
  • Constant, Variable & Gradient
  • Matrix Operations
  • Eagle Mode vs Graph Mode

Topic 4.3 Datasets

  • MNIST Handwritten Digits and Fashion Datasets
  • CIFAR Image Dataset
  • IMDB Text Dataset

Topic 4.4 Neural Network for Regression

  • Introduction to Neural Network (NN)
  • Activation Function
  • Loss Function and Optimizer
  • Machine Learning Methodology
  • Build a NN Predictive Regression Model
  • Load and Save Model

Topic 4.5 Neural Network for Classification

  • Softmax
  • Cross Entropy Loss Function
  • Build a NN Classification Model

Day 5
Module 5 Advanced Neural Networks with Tensorflow

Topic 5.1 Convolutional Neural Network (CNN)

  • Introduction to Convolutional Neural Network (CNN)
  • Convolution & Pooling
  • Build a CNN Model for Image Recognition
  • Overfitting and Underfitting Issues
  • Methods to Solve Overfitting
  • Small Dataset Overfitting Issue
  • Data Augmentation & Dropout

Topic 5.2 Recurrent Neural Network (RNN)

  • Introduction to Recurrent Neural Network (RNN)
  • Types of RNN Architectures
  • LSTM and GRU
  • Word Embedding
  • Build a RNN Model for Text Classification

Topic 5.3 Transfer Learning & Tensorflow Hub

  • Introduction to Transfer Learning
  • Pre-trained Models
  • Tensorflow Hub
  • Transfer Learning for Feature Extraction & Fine Tuning


Course Admin


The learner must meet the minimum requirement below :

  • Read, write, speak and understand English

Target Audience

  • NSF
  • Full Time Students
  • Data Analysts

Software Requirement

This course will use Google Colab for training. Please ensure you have a Google account.

Funding Validity Period

Valid from 13 May 2019 to 31 Mar 2021

Mode of Training

Instructor-led Classroom Training

CITREP+ Claim Procedure

Trainees who wish to claim for CITREP+ funding must submit their online claim applications to IMDA via ICMS upon course or certification completion. Please refer to the Claim Application Guide for detailed application procedures.

For Organisation-Sponsored Trainees, the claim application will be submitted by the sponsoring organisation.

For Self-Sponsored Trainees, the claim application has to be completed by the individual.

All claims for CITREP+ disbursement must be submitted to IMDA within three (3) months from completion date of the last examination or final post-training assessment. Late submissions will not be accepted. Applications with incomplete supporting documents will be rejected for processing.

CITREP+ Funding Support

Category Type Training course and certification
Organisation- sponsored Non SMEs Up to 70% of the nett payable course and certification fees, capped at $3,000 per trainee
SMEs Up to 90% of the nett payable course and certification fees, capped at $3,000 per trainee
Professionals (40 years old and above)
Self-Sponsored Professionals Up to 70% of the nett payable course and certification fees, capped at $3,000 per trainee
Professionals (40 years old and above) Up to 90% of the nett payable course and certification fees, capped at $3,000 per trainee
Students and/or Full-Time National Service (NSF) Up to 100% of the nett payable course and certification fees, capped at $2,500 per trainee


Who Should Attend

  • NSF or Full Time Students
  • Data Analysts
  • Machine Learning Engineers and Developers


Machine Learning TrainerAmir Othman is a software engineer by profession. Being educated in Bauhaus Universität Weimar and Hochschule Ulm, he brings experiences from different facades of the world.With expertise in web technology, natural language processing and machine learning, he is a freelance data scientist. Some of his works include two international news aggregator : and

He also holds an impressive port folio for data visualizations, primarily focusing on web based techniques. After the realization set in that, he does not want to make it as an electronic engineer, he took the decision to go and try something new out of pure curiosity and thirst for new adventure. It didn't come quite handy but he has changed his major three times. It's not a surprise that he studied artificial intelligence and found himself all over again. He has a strong passion for machine learning and data science, fueled by the drive to learn and the endurance for growth beyond the ordinary.

Tensorflow TrainerMuhammad Samer Sallam is a software engineering and data Scientist with more than 3 years’ experience in the field of machine learning/ deep learning. He has a great passion for data science, intelligent-seeming algorithms and web technologies to develop smart web products improving human life. His interest led him to achieve comprehensive experiences in C#, Python, MATLAB, HTML & CSS, Javascript, and Mysql.His Work experiences are as below:

  • Control and Automation Engineer at Damascus International Airport,
  • Damascus (Syria) Research and Development Team Leader at Rachis Systems, Kuala Lumpur (Malaysia)
  • Former Machine Learning Specialist in Abundent, Kuala Lumpur (Malaysia)

Write Your Own Review

You're reviewing: 5 Days Machine Learning Specialization

How do you rate this product? *

  1 star 2 stars 3 stars 4 stars 5 stars
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
  • Reload captcha
    Attention: Captcha is case sensitive.

Product Subjects

Use spaces to separate Subjects. Use single quotes (') for phrases.

You May Be Interested In These Courses