| CODE | CCE5109 | ||||||||||||
| TITLE | Algorithm Deployment | ||||||||||||
| UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | ||||||||||||
| MQF LEVEL | 7 | ||||||||||||
| ECTS CREDITS | 5 | ||||||||||||
| DEPARTMENT | Communications and Computer Engineering | ||||||||||||
| DESCRIPTION | The study-unit covers topics in technology and methods that enable the deployment in production of signal processing and machine learning algorithms. The study-unit provides the student with the specialised knowledge required in professional and industrial settings. The following topics will be covered: Maximizing speed and performance of machine learning algorithms; Cloud APIs useful for developing applications in machine learning and computer vision; Scalable inference on the cloud; Real-time computer vision classification; Embedded machine learning at the edge. Study-Unit Aims: The aims of this study-unit are: - To provide the student with the technological knowledge and skills required to deploy in production the algorithms studied in the more theoretical study-units; - To provide the student with the experience in building a number of example use cases. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Outline and compare model compression techniques; - List and describe typical platforms suitable for edge processing, including GPU based and TPU based systems; - Describe and contrast standards of data ingestion techniques, including messaging systems for real-time and off-line systems; - Explain the advantages of container technology suitable for deploying models at the various layers of the system; - Identify and define tools for monitoring system performance. 2. Skills: By the end of the study-unit the student will be able to: - Select and implement the appropriate computational infrastructure; - Evolve prototype code to production ready code; - Apply code versioning systems; - Deploy and analyze models at mist/fog/cloud layers; - Deploy and analyze models on edge devices; - Select, setup and experiment with data ingestion systems for various kinds of data formats including perceptual signals; - Explore and analyse ways to handle multiple requests simultaneously. Main Text: - Anirudh Koul, Siddha Ganju, Meher Kasam, “Practical Deep Learning for Cloud, Mobile, and Edge: Real-World AI & Computer-Vision Projects Using Python, Keras & TensorFlow”, 1st Edition, October 2019, O’Reilly Media Inc, ISBN 978-1-492-03486-5. |
||||||||||||
| ADDITIONAL NOTES | Pre-requisite Qualifications: Computer Programming Co-requisite Study-units: Machine Learning and Signal Processing |
||||||||||||
| STUDY-UNIT TYPE | Lecture | ||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||
| LECTURER/S | |||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2025/6. It may be subject to change in subsequent years. |
|||||||||||||