recentpopularlog in

deepLearning

« earlier   
ONNX
ONNX is a open format to represent deep learning models. With ONNX, AI developers can more easily move models between state-of-the-art tools and choose the combination that is best for them. ONNX is developed and supported by a community of partners.
deeplearning  artificialintelligence  ai  neuralnetworks 
yesterday by ianchanning
Twitter
Playing around with Veremin, a video theremin by and that uses a PoseNet
DeepLearning  tfjs  from twitter_favs
2 days ago by chrispoole
東京大学など、人の触れている対象の硬さ柔らかさを映像ベースで推定するCNNを用いた手法を発表 | Seamless
面白い。確かに硬さを指定したオブジェクトに触れた時のフィードバックの制御信号を生成するなどVRへの転用に期待できそう。
vr  deeplearning  haptics 
3 days ago by slnbookmark
[1901.04436] Bayesian Learning of Neural Network Architectures
In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distributions over these parameters. Our results show that regular networks with a learnt structure can generalise better on small datasets, while fully stochastic networks can be more robust to parameter initialisation. The proposed method relies on standard neural variational learning and, unlike randomised architecture search, does not require a retraining of the model, thus keeping the computational overhead at minimum.
Bayesian  deeplearning 
3 days ago by hustwj

Copy this bookmark:





to read