-
1
Tie strength in question answer on social network sites
Published 2012“…We present a study evaluating the role of tie strength in question answers. We used previous research on tie strength in social media to generate tie strength information between participants and their answering friends, and asked them for feedback about the value of answers across several dimensions. …”
Get full text
Get full text
Get full text
Article -
2
Functional geometry alignment and localization of brain areas
Published 2012Get full text
Get full text
Article -
3
-
4
Learning an atlas of a cognitive process in its functional geometry
Published 2012Get full text
Get full text
Article -
5
Adversarial examples are not bugs, they are features
Published 2021“…Finally, we present a simple setting where we can rigorously tie the phenomena we observe in practice to a misalignment between the (human-specified) notion of robustness and the inherent geometry of the data.…”
Get full text
Article -
6
The Voronoi game on graphs and its complexity
Published 2019“…When both players play optimally, the first player wins when k is odd, and the game ends in a tie for even k. Next we show that the discrete Voronoi game is intractable in general. …”
Get full text
Article -
7
The Voronoi game on graphs and its complexity
Published 2014“…When both players play optimally, the first player wins when k is odd, and the game ends in a tie for even k. Next we show that the discrete Voronoi game is intractable in general. …”
Get full text
Get full text
Article -
8
Unfolding Genus-2 Orthogonal Polyhedra with Linear Refinement
Published 2018“…Our unfolding algorithm relies on the existence of at most 2 special leaves in what we call the “unfolding tree” (which ties back to the genus), so unfolding polyhedra of genus 3 and beyond requires new techniques.…”
Get full text
Get full text
Article -
9
Unfolding Genus-2 Orthogonal Polyhedra with Linear Refinement
Published 2018“…Our unfolding algorithm relies on the existence of at most 2 special leaves in what we call the “unfolding tree” (which ties back to the genus), so unfolding polyhedra of genus 3 and beyond requires new techniques. …”
Get full text
Get full text
Article -
10
Feedback controller parameterizations for reinforcement learning
Published 2011“…Reinforcement Learning offers a very general framework for learning controllers, but its effectiveness is closely tied to the controller parameterization used. Especially when learning feedback controllers for weakly stable systems, ineffective parameterizations can result in unstable controllers and poor performance both in terms of learning convergence and in the cost of the resulting policy. …”
Get full text
Get full text
Article -
11
Selective Sharing for Multilingual Dependency Parsing
Published 2014“…The algorithm learns which aspects of the source languages are relevant for the target language and ties model parameters accordingly. The model factorizes the process of generating a dependency tree into two steps: selection of syntactic dependents and their ordering. …”
Get full text
Get full text
Article -
12
Word Embeddings as Metric Recovery in Semantic Spaces
Published 2021“…Framing word embedding as metric recovery of a semantic space unifies existing word embedding algorithms, ties them to manifold learning, and demonstrates that existing algorithms are consistent metric recovery methods given co-occurrence counts from random walks. …”
Get full text
Article -
13
Multi-view latent variable discriminative models for action recognition
Published 2014“…Knowledge about the underlying structure of the data is formulated as a multi-chain structured latent conditional model, explicitly learning the interaction between multiple views using disjoint sets of hidden variables in a discriminative manner. The chains are tied using a predetermined topology that repeats over time. …”
Get full text
Get full text
Article -
14
Mahimahi: A Lightweight Toolkit for Reproducible Web Measurement
Published 2015“…Finally, Mahimahi is not inherently tied to browsers and can be used to evaluate many different applications. …”
Get full text
Get full text
Get full text
Get full text
Article -
15
Temporal Grounding Graphs for Language Understanding with Accrued Visual-Linguistic Context
Published 2018“…A robot's ability to understand or ground natural language instructions is fundamentally tied to its knowledge about the surrounding world. …”
Get full text
Get full text
Get full text
Get full text
Article -
16
Label Fusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes
Published 2021“…Deep neural network (DNN) architectures have been shown to outperform traditional pipelines for object segmentation and pose estimation using RGBD data, but the performance of these DNN pipelines is directly tied to how representative the training data is of the true data. …”
Get full text
Article -
17
Bayesian Policy Search with Policy Priors
Published 2014“…Importantly, this algorithm’s search bias is directly tied to the prior and its MCMC proposal kernels, which means we can draw on the full Bayesian toolbox to express the search bias, including nonparametric priors and structured, recursive processes like grammars over action sequences. …”
Get full text
Get full text
Get full text
Article -
18
Multimodal estimation and communication of latent semantic knowledge for robust execution of robot instructions
Published 2021“…A robot’s ability to interpret and execute commands is fundamentally tied to its semantic world knowledge. Commonly, robots use exteroceptive sensors, such as cameras or LiDAR, to detect entities in the workspace and infer their visual properties and spatial relationships. …”
Get full text
Article