Zobrazeno 1 - 10
of 606
pro vyhledávání: '"WOOD, FRANK"'
Inter-neuron communication delays are ubiquitous in physically realized neural networks such as biological neural circuits and neuromorphic hardware. These delays have significant and often disruptive consequences on network dynamics during training
Externí odkaz:
http://arxiv.org/abs/2407.05494
Diffusion models have shown exceptional capabilities in generating realistic videos. Yet, their training has been predominantly confined to offline environments where models can repeatedly train on i.i.d. data to convergence. This work explores the f
Externí odkaz:
http://arxiv.org/abs/2406.04814
Autor:
Lavington, Jonathan Wilder, Zhang, Ke, Lioutas, Vasileios, Niedoba, Matthew, Liu, Yunpeng, Green, Dylan, Naderiparizi, Saeid, Liang, Xiaoxuan, Dabiri, Setareh, Ścibior, Adam, Zwartsenberg, Berend, Wood, Frank
The training, testing, and deployment, of autonomous vehicles requires realistic and efficient simulators. Moreover, because of the high variability between different problems presented in different autonomous systems, these simulators need to be eas
Externí odkaz:
http://arxiv.org/abs/2405.04491
Autor:
Green, Dylan, Harvey, William, Naderiparizi, Saeid, Niedoba, Matthew, Liu, Yunpeng, Liang, Xiaoxuan, Lavington, Jonathan, Zhang, Ke, Lioutas, Vasileios, Dabiri, Setareh, Scibior, Adam, Zwartsenberg, Berend, Wood, Frank
Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames. While such approaches have led to significant progress on st
Externí odkaz:
http://arxiv.org/abs/2405.00251
Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly observed data. However, current simulation-based amorti
Externí odkaz:
http://arxiv.org/abs/2404.09636
Autor:
Manduchi, Laura, Pandey, Kushagra, Bamler, Robert, Cotterell, Ryan, Däubener, Sina, Fellenz, Sophie, Fischer, Asja, Gärtner, Thomas, Kirchler, Matthias, Kloft, Marius, Li, Yingzhen, Lippert, Christoph, de Melo, Gerard, Nalisnick, Eric, Ommer, Björn, Ranganath, Rajesh, Rudolph, Maja, Ullrich, Karen, Broeck, Guy Van den, Vogt, Julia E, Wang, Yixin, Wenzel, Florian, Wood, Frank, Mandt, Stephan, Fortuin, Vincent
The field of deep generative modeling has grown rapidly and consistently over the years. With the availability of massive amounts of training data coupled with advances in scalable unsupervised learning paradigms, recent large-scale generative models
Externí odkaz:
http://arxiv.org/abs/2403.00025
In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on past data.
Externí odkaz:
http://arxiv.org/abs/2402.09542
Autor:
Niedoba, Matthew, Green, Dylan, Naderiparizi, Saeid, Lioutas, Vasileios, Lavington, Jonathan Wilder, Liang, Xiaoxuan, Liu, Yunpeng, Zhang, Ke, Dabiri, Setareh, Ścibior, Adam, Zwartsenberg, Berend, Wood, Frank
Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased neural network approximations or high variance Monte Carlo estimators
Externí odkaz:
http://arxiv.org/abs/2402.08018
Autor:
Niedoba, Matthew, Lavington, Jonathan Wilder, Liu, Yunpeng, Lioutas, Vasileios, Sefas, Justice, Liang, Xiaoxuan, Green, Dylan, Dabiri, Setareh, Zwartsenberg, Berend, Scibior, Adam, Wood, Frank
Simulation of autonomous vehicle systems requires that simulated traffic participants exhibit diverse and realistic behaviors. The use of prerecorded real-world traffic scenarios in simulation ensures realism but the rarity of safety critical events
Externí odkaz:
http://arxiv.org/abs/2309.12508
The maximum likelihood principle advocates parameter estimation via optimization of the data likelihood function. Models estimated in this way can exhibit a variety of generalization characteristics dictated by, e.g. architecture, parameterization, a
Externí odkaz:
http://arxiv.org/abs/2307.16463