Home /
Research
Showing 43 - 48 / 897
Algebraically-Informed Deep Networks (AIDN): A Deep Learning Approach to Represent Algebraic Structures
MustafaHajij, GhadaZamzmi, MatthewDawson....
Published date-12/02/2020
One of the central problems in the interface of deep learning and mathematics is that of building learning systems that can automatically uncover underlying mathematical laws from observed data. In …
Policy Supervectors: General Characterization of Agents by their Behaviour
AnssiKanervisto, TomiKinnunen, VilleHautamäki....
Published date-12/02/2020
DecisionMaking, ImitationLearning
By studying the underlying policies of decision-making agents, we can learn about their shortcomings and potentially improve them. Traditionally, this has been done either by examining the agent's implementation, its …
PlueckerNet: Learn to Register 3D Line Reconstructions
LiuLiu, HongdongLi, HaodongYao....
Published date-12/02/2020
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions. This paper proposes a neural network …
Dataset for eye-tracking tasks
IldarRakhmatulin....
Published date-12/02/2020
EyeTracking
In recent years many different deep neural networks were developed, but due to a large number of layers in deep networks, their training requires a long time and a large …
Chair Segments: A Compact Benchmark for the Study of Object Segmentation
LeticiaPinto-Alva, IanK.Torres, RosangelGarcia....
Published date-12/02/2020
ImageClassification, ObjectDiscovery, SemanticSegmentation, TransferLearning
Over the years, datasets and benchmarks have had an outsized influence on the design of novel algorithms. In this paper, we introduce ChairSegments, a novel and compact semi-synthetic dataset for …
DERAIL: Diagnostic Environments for Reward And Imitation Learning
PedroFreire, AdamGleave, SamToyer....
Published date-12/02/2020
ImitationLearning
The objective of many real-world tasks is complex and difficult to procedurally specify. This makes it necessary to use reward or imitation learning algorithms to infer a reward or policy …