About the Course

This course is an introduction to the foundations of deep learning for more advanced modules, such as computer vision. By the end of this course, participants will have a firm understanding of the concepts of neural network such as neural network architectures, feed-forward networks, backpropagation, keras and dropout.

Examples of simple Artificial Neural Networks will be applied to topics covered in classical machine learning to compare and contrast the performance of the two different approaches.  

  • Course Outline

    Introduction to Neural Network
    • Differences Between Classical Programming and Machine Learning
    • Learning Representations
    • What is Deep Learning
    • Learning Neural Networks
    • Why Now? Building Blocks of Neural Networks
    • Motivational Example 1
    • Building Block of Neural Networks
    • Data Preprocessing and Feature Engineering
    • Tensors
    • Tensor Operations
    • Gradient Based Optimisation Getting Started with Neural Networks
    • Getting Started with Neural Networks and Deep Learning Libraries
    • Binary Classification
    • Multiclass Classification
    • Regression Fundamentals of Machine Learning
    • Categories of Machine Learning
    • Over and Underfitting
    • Machine Learning Workflow
  • Target Participants

    Suitable for finance professionals, entrepreneurs, investment professional, technologist who are looking to gain deep skills in Artificial Intelligence  

  • Certification

    Certificate of completion
  • Admission Requirements

    No minimum entry requirement  
  • Course schedule (conducting days & time)

    E-Learning (Self-paced)

    Course fee payment provides 180 days of course access. Certificate will be awarded upon successful completion within the 180 days.  

  • What You'll Study

  • Course Fees and Funding

    Please refer to course brochure.

  • Contact for course enquiries

  • Remarks

    NYP reserves the right to reschedule/cancel any prog and amend the fees/info without prior notice.