Geoffrey Hinton,被称为“神经网络之父”、“深度学习鼻祖”,他曾获得爱丁堡大学人工智能的博士学位,并且为多伦多大学的特聘教授。在2012年,Hinton还获得了加拿大基廉奖(Killam Prizes,有“加拿大诺贝尔奖”之称的国家最高科学奖)。2013年,Hinton 加入谷歌并带领一个AI团队,他将神经网络带入到研究与应用的热潮,将“深度学习”从边缘课题变成了谷歌等互联网巨头仰赖的核心技术,并将反向传播算法应用到神经网络与深度学习。

VIP内容

在一个持续的循环,在这个循环中,对对抗攻击更强的防御随后被更高级的防御感知攻击打破。我们提出了一种结束此循环的新方法,即通过使攻击者生成语义上类似于攻击目标类的输入来“转移”对抗攻击。为此,我们首先提出一种基于胶囊网络的更强大的防御,它结合了三种检测机制来实现对标准攻击和防御感知攻击的最新检测性能。然后,我们进行了一项人体研究,要求参与者对攻击产生的图像进行标记,结果表明,针对我们的防御系统的未检测到的攻击通常与对抗目标类相似。这些攻击图像不能再被称为“对抗性的”,因为我们的网络像人类一样对它们进行分类。

成为VIP会员查看完整内容
0
13

最新论文

Capsules are the name given by Geoffrey Hinton to vector-valued neurons. Neural networks traditionally produce a scalar value for an activated neuron. Capsules, on the other hand, produce a vector of values, which Hinton argues correspond to a single, composite feature wherein the values of the components of the vectors indicate properties of the feature such as transformation or contrast. We present a new way of parameterizing and training capsules that we refer to as homogeneous vector capsules (HVCs). We demonstrate, experimentally, that altering a convolutional neural network (CNN) to use HVCs can achieve superior classification accuracy without increasing the number of parameters or operations in its architecture as compared to a CNN using a single final fully connected layer. Additionally, the introduction of HVCs enables the use of adaptive gradient descent, reducing the dependence a model's achievable accuracy has on the finely tuned hyperparameters of a non-adaptive optimizer. We demonstrate our method and results using two neural network architectures. First, a very simple monolithic CNN that when using HVCs achieved a 63% improvement in top-1 classification accuracy and a 35% improvement in top-5 classification accuracy over the baseline architecture. Second, with the CNN architecture referred to as Inception v3 that achieved similar accuracies both with and without HVCs. Additionally, the simple monolithic CNN when using HVCs showed no overfitting after more than 300 epochs whereas the baseline showed overfitting after 30 epochs. We use the ImageNet ILSVRC 2012 classification challenge dataset with both networks.

0
0
下载
预览
Top