EE709 Advanced Computational Learning Methods and Applications

Information

Course Goal / Objective

Understand the definition of a range of neural network models; Be able to derive and implement optimisation algorithms for these models; Understand neural implementations of attention mechanisms and sequence embedding models; Be able to implement and evaluate common neural network models for different datasets; Have a good understanding of the two numerical approaches to learning (optimization and integration) and how they relate to the Bayesian approach; Have an understanding of how to choose a model to describe a particular type of data; Know how to evaluate a learned model in practice; Understand the mathematics necessary for constructing novel neural networks solutions.

Course Content

This is an advanced course on the advanced topics of neural networks, focusing on recent developments in deep learning with neural networks such as Bayesian neural networks. The course will focus on data processing and computer vision applications, especially those involving different topics. Recent statistical techniques based on neural networks have led to considerable commercial and academic interest, with considerable progress in these areas. The course will introduce the mathematical definitions of the relevant neural network models and will cover a number of applications of neural networks that can implement related optimization algorithms and convert them into at least one conference paper, such as analyzing hidden dimensions in the data.

Course Precondition

Resources

Notes

Course Learning Outcomes

Relation with Program Learning Outcome

Week Plan