Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Krell, Mario Michael"'
Autor:
Helal, Hatem, Firoz, Jesun, Bilbrey, Jenna, Krell, Mario Michael, Murray, Tom, Li, Ang, Xantheas, Sotiris, Choudhury, Sutanay
Molecular property calculations are the bedrock of chemical physics. High-fidelity \textit{ab initio} modeling techniques for computing the molecular properties can be prohibitively expensive, and motivate the development of machine-learning models t
Externí odkaz:
http://arxiv.org/abs/2211.13853
Autor:
Krell, Mario Michael, Lopez, Manuel, Anand, Sreenidhi, Helal, Hatem, Fitzgibbon, Andrew William
When processing a batch of graphs in machine learning models such as Graph Neural Networks (GNN), it is common to combine several small graphs into one overall graph to accelerate processing and remove or reduce the overhead of padding. This is for e
Externí odkaz:
http://arxiv.org/abs/2209.06354
Publikováno v:
Journal of Neural Engineering 14 2 (2017) 025003
Objective: Classifier transfers usually come with dataset shifts. To overcome them, online strategies have to be applied. For practical applications, limitations in the computational resources for the adaptation of batch learning algorithms, like the
Externí odkaz:
http://arxiv.org/abs/2208.05112
Autor:
Lee, Edward H., Krell, Mario Michael, Tsyplikhin, Alexander, Rege, Victoria, Colak, Errol, Yeom, Kristen W.
Differentially private SGD (DPSGD) has recently shown promise in deep learning. However, compared to non-private SGD, the DPSGD algorithm places computational overheads that can undo the benefit of batching in GPUs. Micro-batching is a common method
Externí odkaz:
http://arxiv.org/abs/2109.12191
Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding tokens, so th
Externí odkaz:
http://arxiv.org/abs/2107.02027
Origami is becoming more and more relevant to research. However, there is no public dataset yet available and there hasn't been any research on this topic in machine learning. We constructed an origami dataset using images from the multimedia commons
Externí odkaz:
http://arxiv.org/abs/2101.05470
Epidemiology models are central in understanding and controlling large scale pandemics. Several epidemiology models require simulation-based inference such as Approximate Bayesian Computation (ABC) to fit their parameters to observations. ABC inferen
Externí odkaz:
http://arxiv.org/abs/2012.14332
Autor:
Krell, Mario Michael, Wehbe, Bilal
Regression evaluation has been performed for decades. Some metrics have been identified to be robust against shifting and scaling of the data but considering the different distributions of data is much more difficult to address (imbalance problem) ev
Externí odkaz:
http://arxiv.org/abs/2009.05176
Multi-context model learning is crucial for marine robotics where several factors can cause disturbances to the system's dynamics. This work addresses the problem of identifying multiple contexts of an AUV model. We build a simulation model of the ro
Externí odkaz:
http://arxiv.org/abs/1809.06179
Autor:
Krell, Mario Michael
Publikováno v:
PhD Thesis, University of Bremen, Bremen, 1-236, 2015
The classification of complex data usually requires the composition of processing steps. Here, a major challenge is the selection of optimal algorithms for preprocessing and classification (including parameterizations). Nowadays, parts of the optimiz
Externí odkaz:
http://arxiv.org/abs/1801.04929