Step 1: Enroll in the training course

Deep Learning in Computer Vision Course

Duration: 12 days | Intake: 21 September 2020

Deep Learning is driving advances in the field of Computer Vision that are changing our world. Robots and machines can now “see”, learn and respond from their environment. 

About This Course

This course will further elaborate on the underlying Deep Learning techniques used in Computer Vision systems and prepares you to be a Deep Learning engineer. It is developed by Certifai’s Deep Learning engineers with years of practical experience in this field.

What You'll Learn

  • The many techniques of Deep Learning in Computer Vision, from image processing, image classification, object detection to image segmentation
  • Hands-on experience in building advanced deep learning models such as Convolutional Neural Network, YOLO and others
  • Learn how to practice and evaluate these ideas in the deep learning framework, Deeplearning4j (DL4J).

Course Outline

Module 1 : Introduction to Machine Learning

This module explains how Machine Learning works, elaborates its goals and the many different techniques used to achieve them.

Module 2 : Introduction to Deep Learning and FNN

In this module, you will learn the fundamentals of Deep Learning and how the first and simplest type of artificial neural network devised known as the Feedforward Neural Network (FNN) works.

Module 3 : Convolutional Neural Network

Convolutional Neural Networks are being used in identifying faces, objects, and traffic signs. This module will show you how it is done all the way down to the details.

Module 4 : Recurrent Neural Network

The descendant of the FNN, the RNNs are designed to recognize a data’s sequential characteristics and use patterns to predict the next likely scenario. This module will teach you how they work in identifying human speech and language.

Module 5 : Image Processing

Image Processing is a type of signal processing in which input is an image and output may be the characteristics associated with that image. This module will elaborate on how it works and why it is so widely used.

Module 6 : Image Classification

Among the more important aspects of digital image analysis, Image Classification helps the computer identify and portray the features occurring in an image. This module explains what goes into making it happen and how can it be improved.

Module 7 : Object Detection

Object detection deals with detecting instances of objects of a certain class in digital images and videos, commonly seen in pedestrian detection systems. The module will demonstrate how you could build one on your own and understand its potential.

Module 8 : Segmentation With Deep Learning

Image segmentation sorts pixels into larger components, eliminating the need to consider individual pixels as units of observation. The module will show you how segmentation is made possible with Deep Learning.

Module 9 : Facial Recognition

In this final module, you will be exposed to facial recognition, a system commonly associated with security be it on your phone or in a facility while learning its building blocks and how it is made better with Deep Learning.


  • Well-versed in the Java programming language
  • Possess good knowledge in calculus
  • Exposure to the deep learning framework, Deeplearning4j (DL4J)

Keng Hooi Teoh


As a Senior Deep Learning Engineer at CertifAI, Keng Hooi develops computer vision applications using deep learning algorithms. With his experience in data science consultancy and training, Keng Hooi drives training and advocacy initiatives at Skymind for Malaysia’s developer community.

Step 2: Sit for the exam

Deep Learning Certification in Computer Vision