Python for Machine and Deep Learning

From Machine Learning to Convolutional Neural Network 

Starting from machine learning, we move towards deep learning to give you details understanding on how and why it works!  

 enquire icon

The Deep Learning Research Becomes More Effective Thanks to Open Source Softwares...

Course Synopsis


Artificial Intelligence (AI) is any theory and development that make a machine thinks like human beings, which has trigger the interest of scientists and researchers since early 1950s. AI development includes the explicitly programmed algorithms, such as fuzzy logic and expert system, to the learning system, such as neural network. 

Machine Learning is a subset of Artificial Intelligence, in which a system is focused on training system to perform tasks by giving the machine training data. The word “learning” define the scope of the systems in which the system would learn either by supervised or unsupervised training. The former systems include neural network and support vector machine, and the latter includes self-organizing map and various clustering approaches. 

This training would focus in machine learning and then gradually guide participants to deep learning, which is the subset of the machine learning with more hidden layers in the network. The participants would go through the hands-on from the basic machine learning to deep learning. The training would be conducted mainly using Python, with the packages such as TensorFlow, Keras, and others. 

Course Objectives

This is a hands-on application course that provides step-by-step description while concentrating on useful tips and tricks to machine learning and deep learning system. Participants will be introduced to various algorithms through practical sessions with plenty of Python code examples and exercises for real-world applications.


Who Must Attend

Lecturers, students, programmers, developers, engineers and simply anyone who would like to work on intelligence systems for their projects are encouraged to attend the course.



Candidates must have experience with any programming language, preferably and with knowledge in statistics and linear algebra.


Course Outline

Day 1

Artificial Intelligence, Machine Learning, or Deep Learning?

This section will discuss the differences among artificial intelligence, machine learning, and deep learning. At the end of section, participants will setup their own laptop with the modules for the training.

  •  Introduction to Artificial Intelligence and the current development
  • Introduction to various types of Machine Learning system
  • Introduction to Deep Learning and the current states and variants 
  • Machine learning development tools for Python 
  • Hands-on: Setting up Development Environment

 Step-by-Step Guideline to work with Machine Learning Systems

This section will cover the flow while working with machine learning. The flow is important in order to achieve near-human performance. 

  •  Preparing Data 
  • Selection and Evaluation of Model 
  • Tuning the Hyperparameter
  • Bias–variance Tradeoff 
  • Hands-on: Building Basic Machine Learning System

 Supervised and Unsupervised Learning Systems

This section will give the participants an overview of supervised and unsupervised learning system. The remaining sections of the course will focus on supervised learning systems.  

  •  Supervised and Unsupervised Learning
  • Overview of Unsupervised Learning
  • The Basic of Supervised Training: Classification and Regression
  • Going Further in Supervised Machine Algorithms
  • Hands-on: An Support Vector Machine (SVM) Classifier for Digits Recognition (MNIST Dataset)
  • Hands-on: A Shallow Neural Network (NN) Classifier for Digits Recognition (MNIST Dataset)

Day 2

From Machine Learning to Deep Learning

This section will show how the deep learning break through the bottle neck of machine learning with the help of GPU training.

  •  Shallow Neural Network and Deep Neural Network 
  • Why Deep Learning? 
  • Deep Learning Algorithms Types and Variants
  • Hands-on: A Deep Learning System for Handwritten Digit Recognition (MNIST Dataset)

 Convolution Neural Networks (CNN)

This section will provide hands-on exercise on the CNN, which is one of the most popular deep learning architectures due to its outstanding performance in human perceptual related problems.

  •  Image Fundamentals
  • What is Correlation and Convolutions?
  • Typical Architectures of CNN 
  • Hands-on: Training CNN for Basic Image Classification
  • Serializing and Loading CNN Models
  • Transfer Learning
  • Hands-on: Using Transfer Learning on Pre-trained CNN Models

 enquire icon


© 2010-2018 Trity Technologies Sdn Bhd. All Rights Reserved.