What is the translation of " 对神经网络 " in English?

• neural network
• neural networks

Examples of using 对神经网络 in Chinese and their translations into English

也许您对神经网络早有所耳闻。?
Perhaps you have heard of neural networks?

但对神经网络的热潮直到2010年代初才真正兴起。
But interest in neural networks didn't truly take off until the early 2010s.

而这次宣言也再次点燃了他对神经网络研究的激情。
The declaration reignited his passion for neural networks research.

但是传统的计算机并没有对神经网络操作进行优化。
But traditional computers are not optimized for neural network operations.

这一宣言重新点燃了他对神经网络研究的热情。
The declaration reignited his passion for neural networks research.

这个宣言重新点燃了他对神经网络研究的热情。
The declaration reignited his passion for neural networks research.

让我们对神经网络进行1500次训练迭代，看看会发生什么。
Let's train the Neural Network for 1500 iterations and see what happens.

研究人员使用了5000多张经专业编辑的照片对神经网络进行训练，教会它与一张“好”照片相关的特殊编辑规则。
The researchers fed the neural network more than 5,000 professionally edited photos, which taught it specific editing rules associated with“good” photos.

我们对神经网络进行训练，让它找出一张照片、一段视频乃至实时视频流中的不同对象。
We trained neural networks to finds to find different objects on a photo/video and even on a live stream video.

然而，有时候很难将这些特征表示成对神经网络有用的输入并将其与现有特征结合起来。
However, it is sometimes very hard to make data representations that are useful for neural network input and combine them with existing features.

ResNet则从根本上改变了我们对神经网络及其学习方式的理解。
ResNet fundamentally changed the way we understand neural networks and how they learn.

嵌入式MIPS核心将加强Wave的创新数据流技术，以实现对神经网络图的快速高效处理。
The embedded MIPS core will enhance Wave's innovative dataflow technology, which en-ables fast and efficient processing of neural network graphs.

然而，他同样认为，「最大的问题」在于这种语言是如何对深层神经网络施加影响的。
But at the moment, he says, the"big question" is how this language affects deep neural networks.

以BVLC在视觉和图像识别领域的成果为基础，Caffe的核心优势在于能够对卷积神经网络（CNN）建模。
Stemming from BVLC's work in vision and image recognition, Caffe's core strength is its ability to model a Convolutional Neural Network(CNN).

奥迪工程师早前利用“无监督式学习（unsupervisedlearning）”技术，助其实现对神经网络的训练工作。
Audi engineers had previously trained the neural network with the help of“unsupervised learning.”.

事实证明，若想得出游戏见解，我们需要使用大量游戏数据对深度神经网络进行训练。
It turns out that surfacing gaming insights requires training a deep neural network on a lot of gaming data.

关于深度学习和决策，我们对神经网络有真正的理论认识吗?
On Deep Learning and Decision Making, Do we have a true theoretical understanding of a neural network?

节点之间低权重的连接对神经网络最终输出结果贡献极小，因此许多连接被去除或者说被修剪掉了。
Low-weight connections between nodes contribute very little to a neural network's final output, so many of them can be safely eliminated, or pruned.

出于这些原因，开发用于发展对神经网络的内部状态的一些理解的方法是非常值得尝试的。
For these reasons, methods for developing some understanding of the internal states of the neural networks are desirable.

最近，科学家们发现，黑客不仅可以对神经网络发起对抗性攻击，也可以对人类发起类似攻击。
Recently, scientists have revealed that it's possible to launch an adversarial attack not only on a neural network but also on a human.

Scikit-learn主要关注经典ML算法，因此它对神经网络的支持非常有限，不能用于深度学习问题。
Scikit-learn focuses mostly on classical ML algorithms, thus it has very limited support for Neural Networks and can't be used for Deep Learning problems.

Jeff对神经网络的了解自本科阶段以来一直没什么进展，于是Heidi看到他们家的卫生间摆满了教材。
Jeff's knowledge of neural networks hadn't advanced much since his undergrad years, and Heidi watched as their bathroom filled with textbooks.

这个过程是对神经网络进行训练的一部分，而不是直接编程的。
This process is part of the training of the neural network and is not directly programmed.

这是理解输入的不同部分对神经网络的不同重要性的常见技术。
This is a common technique for understanding the relative importance of different parts of an input to a neural network.

这项研究对神经网络“固有盲点”以及它们在学习过程中的“非直觉特征”提出了质疑。
The work raised questions about the"intrinsic blind spots" of neural networks and the"non intuitive characteristics" in how they learn.

学习率的选择对神经网络的表现有很大的影响。
The choice of learning rate has a large impact on the performance of the neural network.

Jeff对神经网络的了解自本科阶段以来一直没什么进展，于是Heidi看到他们家的卫生间摆满了教材。
Jeff's knowledge of neural networks has not advanced since his student years, and Heidi watched their bathroom fill with textbooks.

然而，我认为要实现人们对神经网络的夙愿，需要不断的训练，因此需要指数级的能量和成本。
However I do think the ambitions people have for neural networks will demand constant training and therefore require exponential energy and costs.

然后，我们展示了对神经网络的理论上的理解如何帮助我们建立性能上限并更系统地设计网络参数;
We then demonstrate how such theoretical understanding of neural networks can help us to establish a performance limit and design network parameters more systematically;

Scikit-learn主要关注经典ML算法，因此它对神经网络的支持非常有限，不能用于深度学习问题。
Scikit-learn focuses on the classical ML algorithm, so its support for neural networks is very limited and cannot be used for deep learning problems.