Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 70Machine Learning
- 64Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 21Natural Language Processing
- 20Image processing. Digital techniques.
-
Fall 2019
There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively based on deep neural networks, and their training can be unsupervised using stereo image pairs, supervised using LiDAR...
-
Spring 2018
We consider the problem of estimating the location of people as they move and work in indoor environments. More specifically, we focus on the scenario where one of the persons of interest is unable or unwilling to carry a smartphone, or any other âwearableâ device, which frequently arises in...
-
Fall 2018
Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to establish RNNs as an attractive alternative to CRFs for sequence labeling. To do...
-
Spring 2017
A curriculum is a planned sequence of instructions or a view of the student’s experiences in terms of the educator’s or school’s instructional goals. However, the guidance provided by the curriculum is limited and both student and course counsellor struggle with the question of choosing a...
-
Serialization Management Driven Performance in Best-Effort Hardware Transactional Memory Systems
DownloadFall 2014
Serialization Management is the Best-Effort Hardware Transactional Memory (BE-HTM) counterpart to Software Transactional Memory (STM) Contention Management. A serialization manager uses non-speculative serialization to provide a forward-progress guarantee while simultaneously attempting to...