Can physical tools that adapt their shape based on a learner's performance help in motor skill training?

DG Turakhia, Y Qi, LG Blumberg, A Wong… - Proceedings of the …, 2021 - dl.acm.org
… such automatically shape-adapting tools can also help train users … shape can help users
in motor skill training. In particular, we study how training with an automatically adaptive training

[图书][B] Perceptual learning: How experience shapes visual perception

B Dosher, ZL Lu - 2020 - books.google.com
… To what degree does learning generalize to, or perhaps interfere with, new stimuli or related
training protocols better than others, and if so, how can we develop the best form of training

Rapid training of deep neural networks without skip connections or normalization layers using deep kernel shaping

J Martens, A Ballard, G Desjardins, G Swirszcz… - arXiv preprint arXiv …, 2021 - arxiv.org
training fast and generalizing to unseen data, and show how these can be avoided by carefully
controlling the “shape” of … We then develop a method called Deep Kernel Shaping (DKS), …

The emergence of the shape bias results from communicative efficiency

E Portelance, MC Frank, D Jurafsky, A Sordoni… - arXiv preprint arXiv …, 2021 - arxiv.org
… tions: how did the shape bias emerge in our lexical categorization systems? and why does it
… – the proportion of shape games seen during training (the non-shape games are randomly …

Fitness shaping for multiple teams

J Cook, K Tumer - Proceedings of the Genetic and Evolutionary …, 2022 - dl.acm.org
… We provide a fitness shaping approach to training multiple agents to cooperate with multiple
… to train with. The purpose of this second experiment is to show how well these shaped

Plad: Learning to infer shape programs with pseudo-labels and approximate distributions

RK Jones, H Walke, D Ritchie - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
shapes for training, 3K shapes for validation, and 3K shapes … see how different fine-tuning
methods are affected by training … We plot the number of training shapes on the X-axis and test …

Clip-forge: Towards zero-shot text-to-shape generation

A Sanghi, H Chu, JG Lambourne… - Proceedings of the …, 2022 - openaccess.thecvf.com
… for shapes via training an autoencoder, and we then train a normalizing flow network [12] to
model the distribution of shape em… In this experiment, we investigate how much does prompt …

Learning gradient fields for shape generation

R Cai, G Yang, H Averbuch-Elor, Z Hao… - Computer Vision–ECCV …, 2020 - Springer
… Then we describe how to model the distribution of shapes from the set of point clouds (ie \(\…
Then we describe how we train this neural network and how we sample points using the …

Learning canonical shape space for category-level 6d object pose and size estimation

D Chen, J Li, Z Wang, K Xu - Proceedings of the IEEE/CVF …, 2020 - openaccess.thecvf.com
… Second, to overcome the lack of real-world training images with 3D point clouds, … does it
outperform the state-of-the-arts? 3) How capable is our network in terms of single-view shape

Deep learning on a data diet: Finding important examples early in training

M Paul, S Ganguli… - Advances in neural …, 2021 - proceedings.neurips.cc
training dynamics through the lens of important examples—we investigate how the data
distribution shapes the … of the model’s data representation that are relatively stable over training. …