Deep Learning Foundations And Applications

Without a doubt, artificial intelligence is in the progress of transforming numerous industries around the world. Part of the innovation in artificial intelligence has been with the rise of deep learning, which has been at the forefront of this wave surpassing human performance in many aspects of our lives – image recognition, speech recognition, natural language processing, autonomous driving, etc. In practice, deep learning is a subset of machine learning which focuses on learning from data via the use of many-layered neural networks.

In this course, we will start by reviewing the basics of machine learning common practices and models, after which we will then dive into the theory, the practice, and the applications behind deep learning.

During hands-on sessions, which will be conducted using Python, we will be using a number of libraries including Keras/Tensorflow, OpenCV, NumPy/SciPy, scikit-learn, and matplotlib to construct our deep learning system examples.

For hands-on sessions, we will be using Google Colab cloud instances to train and evaluate deep learning models.

Participants will be progressively introduced first to the common machine learning practices and models, followed by a deep dive into deep learning systems and applications.  Interspersed in between the lectures will be interesting and real-world hands-on sessions ranging from standard datasets like Iris/MNIST to defect inspection, and autonomous driving.

What You Will Learn:

• Learn data science and machine learning standard practices, work-flow, and common machine learning models
• Discover state-of-the-art convolution neural network (CNN) architectures and how to apply transfer learning
• Build deep learning systems for real-world applications including defect detection and autonomous driving
• Evaluate and improve the performance of deep learning systems
• Investigate different tasks in the application of CNNs to computer vision including localization and segmentation

Who Should Attend:

• Developers, programmers, and engineers who would like to add an intelligent layer into their applications or find innovative/creative solutions using machine learning to automate their work are encouraged to attend the course.

Prerequisite:

• Competency in Python programming. For those who are new to Python, candidates are advised to attend the Introduction to Python course first.
• Knowledge and understanding of statistics and linear algebra.
• Competency in machine learning. For those who are new to machine learning, candidates are advised to attend the Machine Learning with Python course first.