Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Chang, Oscar"'
Autor:
Weidinger, Laura, Barnhart, Joslyn, Brennan, Jenny, Butterfield, Christina, Young, Susie, Hawkins, Will, Hendricks, Lisa Anne, Comanescu, Ramona, Chang, Oscar, Rodriguez, Mikel, Beroshi, Jennifer, Bloxwich, Dawn, Proleev, Lev, Chen, Jilin, Farquhar, Sebastian, Ho, Lewis, Gabriel, Iason, Dafoe, Allan, Isaac, William
Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to safety eval
Externí odkaz:
http://arxiv.org/abs/2404.14068
Generalization remains a major problem in supervised learning of single-channel speech enhancement. In this work, we propose learnable loss mixup (LLM), a simple and effortless training diagram, to improve the generalization of deep learning-based sp
Externí odkaz:
http://arxiv.org/abs/2312.17255
It has been shown that learning audiovisual features can lead to improved speech recognition performance over audio-only features, especially for noisy speech. However, in many common applications, the visual features are partially or entirely missin
Externí odkaz:
http://arxiv.org/abs/2312.10088
In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training, models need
Externí odkaz:
http://arxiv.org/abs/2312.10087
Autor:
Chang, Oscar, Lipson, Hod
Weight-sharing plays a significant role in the success of many deep neural networks, by increasing memory efficiency and incorporating useful inductive priors about the problem into the network. But understanding how weight-sharing can be used effect
Externí odkaz:
http://arxiv.org/abs/2312.08401
SATNet is an award-winning MAXSAT solver that can be used to infer logical rules and integrated as a differentiable layer in a deep neural network. It had been shown to solve Sudoku puzzles visually from examples of puzzle digit images, and was heral
Externí odkaz:
http://arxiv.org/abs/2312.11522
Hypernetworks are meta neural networks that generate weights for a main neural network in an end-to-end differentiable manner. Despite extensive applications ranging from multi-task learning to Bayesian deep learning, the problem of optimizing hypern
Externí odkaz:
http://arxiv.org/abs/2312.08399
Autor:
Chang, Oscar, Lipson, Hod
The success of gradient-based meta-learning is primarily attributed to its ability to leverage related tasks to learn task-invariant information. However, the absence of interactions between different tasks in the inner loop leads to task-specific ov
Externí odkaz:
http://arxiv.org/abs/2312.08398
Visual speech recognition models extract visual features in a hierarchical manner. At the lower level, there is a visual front-end with a limited temporal receptive field that processes the raw pixels depicting the lips or faces. At the higher level,
Externí odkaz:
http://arxiv.org/abs/2302.10915
Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as "programming
Externí odkaz:
http://arxiv.org/abs/1905.09453