An official website of the United States government
Double groupoids are a type of higher groupoid structure that can arise when one has two distinct groupoid products on the same set of arrows. A particularly important example of such structures is the irrational torus and, more generally, strict 2-groups. Groupoid structures give rise to convolution operations on the space of arrows. Therefore, a double groupoid comes equipped with two product operations on the space of functions. In this article we investigate in what sense these two convolution operations are compatible. We use the representation theory of compact Lie groups to get insight into a certain class of 2-groups.
more »
« less
Poster: DeepFind: Sensor-driven Inference Acceleration for Continuous Deep Mobile Vision Applications
We propose DeepFind, an on-device acceleration engine for mobile-native spatial exploratory applications that utilize deep-learning architectures such as CNNs. DeepFind leverages the fact that input frames exhibit high visual dynamicity, of which a dominant portion actually comes from the camera’s own motion. We develop lightweight sensor-based transformations and perspective-normalized global buffer management to replace expensive convolution operations, effectively speeding up CNN inference. DeepFind achieves a win-win – lightweight reusability determination coupled with avoiding a large amount of convolution operations, creating a virtuous cycle: smaller inter-frame differential leads to faster per-frame computation, yielding even smaller inter-frame differential and so on.
more »
« less
- Award ID(s):
- 1908910
- PAR ID:
- 10201222
- Date Published:
- Journal Name:
- HotMobile '20: Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The fast-paced, volatile nature of hockey makes it a challenging sport to analyze and predict the final outcome. This paper presents two continuous-time Markov process models that predict the probability that a team will win a hockey game given particular states during the game. These states incorporate shot and goal differential relative to the opposing team and are used to approximate the probability that the home team would win depending on the state they are currentlymore » « less
-
The fast-paced, volatile nature of hockey makes it a challenging sport to analyze and predict the final outcome. This paper presents two continuous-time Markov process models that predict the probability that a team will win a hockey game given particular states during the game. These states incorporate shot and goal differential relative to the opposing team and are used to approximate the probability that the home team would win depending on the state they are currently in at a given time in the game. We also provide several examples of using this model to predict National Hockey League games.more » « less
-
The convolution operation plays a vital role in a wide range of critical algorithms across various domains, such as digital image processing, convolutional neural networks, and quantum machine learning. In existing implementations, particularly in quantum neural networks, convolution operations are usually approximated by the application of filters with data strides that are equal to the filter window sizes. One challenge with these implementations is preserving the spatial and temporal localities of the input features, specifically for data with higher dimensions. In addition, the deep circuits required to perform quantum convolution with a unity stride, especially for multidimensional data, increase the risk of violating decoherence constraints. In this work, we propose depth-optimized circuits for performing generalized multidimensional quantum convolution operations with unity stride targeting applications that process data with high dimensions, such as hyperspectral imagery and remote sensing. We experimentally evaluate and demonstrate the applicability of the proposed techniques by using real-world, high-resolution, multidimensional image data on a state-of-the-art quantum simulator from IBM Quantum.more » « less
-
In cooperative multi-agent reinforcement learning (Co-MARL), a team of agents must jointly optimize the team's longterm rewards to learn a designated task. Optimizing rewards as a team often requires inter-agent communication and data sharing, leading to potential privacy implications. We assume privacy considerations prohibit the agents from sharing their environment interaction data. Accordingly, we propose Privacy-Engineered Value Decomposition Networks (PE-VDN), a Co-MARL algorithm that models multi-agent coordination while provably safeguarding the confidentiality of the agents' environment interaction data. We integrate three privacy-engineering techniques to redesign the data flows of the VDN algorithm-an existing Co-MARL algorithm that consolidates the agents' environment interaction data to train a central controller that models multi-agent coordination-and develop PE-VDN. In the first technique, we design a distributed computation scheme that eliminates Vanilla VDN's dependency on sharing environment interaction data. Then, we utilize a privacy-preserving multi-party computation protocol to guar-antee that the data flows of the distributed computation scheme do not pose new privacy risks. Finally, we enforce differential privacy to preempt inference threats against the agents' training data-past environment interactions-when they take actions based on their neural network predictions. We implement PE-VDN in StarCraft Multi-Agent Competition (SMAC) and show that it achieves 80% of Vanilla VDN's win rate while maintaining differential privacy levels that provide meaningful privacy guarantees. The results demonstrate that PE-VDN can safeguard the confidentiality of agents' environment interaction data without sacrificing multi-agent coordination.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
