View Proposal

---

Proposer

Chengjia Wang

Title

PCN: predictive coding network

Goal

Implement predictive coding network and compare it to popular deep learning models on a vision or NLP task

Description

Predictive network is not as famous as the CNN, transformer, diffusion and Mamba models, yet have unbeatable advantages in modern computing system. The aim of this work is to implement PCN to solve one simple vision or NLP task (or processing other types of serial data), and further discover possible approaches to improve its performance and robustness. You need to have a prior knowledge about deep learning models, such as, CNN, MLP, transformer, attention, etc to conduct this research.

Resources

Background

Url

Difficulty Level

Challenging

Ethical Approval

None

Number Of Students

0

Supervisor

Chengjia Wang

Keywords

ai, machine learning, network architecture, vision, nlp, deep learning

Degrees

Bachelor of Science in Computer Science
Bachelor of Science in Computer Systems
Bachelor of Science in Information Systems
Master of Engineering in Software Engineering
Master of Science in Artificial Intelligence
Master of Science in Artificial Intelligence with SMI
Master of Science in Computing (2 Years)
Master of Science in Data Science
Master of Science in Human Robot Interaction
Master of Science in Information Technology (Software Systems)
Master of Science in Robotics
Master of Science in Software Engineering
Bachelor of Science in Computing Science
Bachelor of Engineering in Robotics
Master of Science in Robotics with Industrial Application
Bachelor of Science in Statistical Data Science