Simple and complex activity recognition through smart phones
S Dernbach, B Das, NC Krishnan… - 2012 eighth …, 2012 - ieeexplore.ieee.org
Due to an increased popularity of assistive healthcare technologies activity recognition has
become one of the most widely studied problems in technology-driven assistive healthcare …
become one of the most widely studied problems in technology-driven assistive healthcare …
Quantum walk neural networks with feature dependent coins
S Dernbach, A Mohseni-Kabir, S Pal, M Gepner… - Applied Network …, 2019 - Springer
Recent neural networks designed to operate on graph-structured data have proven effective
in many domains. These graph neural networks often diffuse information using the spatial …
in many domains. These graph neural networks often diffuse information using the spatial …
Cache content-selection policies for streaming video services
The majority of Internet traffic is now dominated by streamed video content. As video quality
continues to increase, the strain that streaming traffic places on the network infrastructure …
continues to increase, the strain that streaming traffic places on the network infrastructure …
Quantum walk neural networks for graph-structured data
S Dernbach, A Mohseni-Kabir, S Pal… - Complex Networks and …, 2019 - Springer
In recent years, neural network architectures designed to operate on graph-structured data
have pushed the state-of-the-art in the field. A large set of these architectures utilize a form of …
have pushed the state-of-the-art in the field. A large set of these architectures utilize a form of …
Deep reinforcement learning with macro-actions
IP Durugkar, C Rosenbaum, S Dernbach… - arXiv preprint arXiv …, 2016 - arxiv.org
Deep reinforcement learning has been shown to be a powerful framework for learning policies
from complex high-dimensional sensory inputs to actions in complex tasks, such as the …
from complex high-dimensional sensory inputs to actions in complex tasks, such as the …
GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding
Integrating large language models with knowledge graphs derived from domain-specific
data represents an important advancement towards more powerful and factual reasoning. As …
data represents an important advancement towards more powerful and factual reasoning. As …
Utilizing Graph Structure for Machine Learning
S Dernbach - 2021 - scholarworks.umass.edu
The information age has led to an explosion in the size and availability of data. This data
often exhibits graph-structure that is either explicitly defined, as in the web of a social network, …
often exhibits graph-structure that is either explicitly defined, as in the web of a social network, …
Stefan Dernbach
D Learning, AS Mahadevan, J Kurose - people.cs.umass.edu
Stefan Dernbach – Curriculum Vitae … Stefan Dernbach … 5506 5th Ave NW Seattle, WA
98107 United States 509-554-2085 dernbach@cs.umass.edu people.cs.umass.edu/~dernbach …
98107 United States 509-554-2085 dernbach@cs.umass.edu people.cs.umass.edu/~dernbach …
Asymmetric node similarity embedding for directed graphs
S Dernbach, D Towsley - Complex Networks XI: Proceedings of the 11th …, 2020 - Springer
Node embedding is the process of mapping a set of vertices from a graph onto a vector
space. Modern deep learning embedding methods use random walks on the graph to sample …
space. Modern deep learning embedding methods use random walks on the graph to sample …
Achieving early and substantial greenhouse gas reductions under a post-Kyoto agreement
JC Dernbach - Geo. Int'l Envtl. L. Rev., 2007 - HeinOnline
… Dernbach can be reached at [email protected]. © 2008, John C. Dernbach. …
Dernbach, Sustainable Development as a Framework for National …
Dernbach, Sustainable Development as a Framework for National …