Recent Additions

• A high performance vector rendering pipeline 

  Ellis, Apollo Isaac Orion (2018-12-05)

  Vector images are images which encode visible surfaces of a 3D scene, in a resolution independent format. Prior to this work generation of such an image was not real time. As such the benefits of using them in the graphics ...

  application/pdf

  PDF (7MB)
• Reinforced co-learning for semi-supervised ranking 

  He, Shibi (2018-12-14)

  Learning to rank is vital to information retrieval and recommendation systems. Directly optimizing the listwise evaluation measure such as normalized discounted cumulative gain (NDCG) is an advanced way to learn a ranking ...

  application/pdf

  PDF (1MB)
• Weakly supervised learning from referring expression: Challenge and directions 

  Dong, Taiyu (2018-12-13)

  We explore methods of weakly supervised learning from referring expression. Unlike traditional fully supervised semantic segmentation of object recognition tasks, in which a a small set of discrete class bases is provided, ...

  application/pdf

  PDF (5MB)
• Improving cache replacement policy using deep reinforcement learning 

  Benson, Christopher Edward (2018-12-13)

  This thesis explores the use of reinforcement learning approaches to improve replacement policies of caches. In today's internet, caches play a vital role in improving performance of data transfers and load speeds. From ...

  application/pdf

  PDF (551kB)
• A node-based approach to charm-FFT 

  Lee, Dong Hun (2018-12-10)

  Parallel 3D Fast Fourier Transform is a communication intensive algorithm that suffers from the unignorable communication overhead. Because the interconnect communication bandwidth is a static component, adjustments to ...

  application/pdf

  PDF (257kB)