Artificial neural networks already run our internet search engines, digital assistants, self-driving cars, Wall Street trading algorithms, and smart phones.

人工神经网络已经在我们的互联网搜索引擎、数字助理、自动驾驶汽车、华尔街交易算法和智能手机中运行。

The team presented the results at the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

研究团队在欧洲人工神经网络、计算智能和机器学习研讨会上展示了他们的研究结果。

Combined with on-policy and off-policy deep reinforcement learning algorithms, NeuEvo achieves comparable performance with artificial neural networks, as shown in the study.

结合政策内外深度强化学习算法，NeuEvo 实现了与人工神经网络相当的性能，如研究所示。

Most notable are artificial neural networks, which were inspired by neurons in our brains!

最著名的是人工神经网络，它的灵感来自我们大脑中的神经元！

Researchers at Purdue University are using artificial neural networks, to decode real neural networks.

普渡大学的研究人员正在使用人工神经网络来解码真实的神经网络。

To understand how they work, imagine an artificial neural network trained to spot birds in images.

为了了解它们的工作原理，想象一下一个经过训练可以识别图像中鸟类的人工神经网络。

Dr Hinton popularised a clever mathematical algorithm known as backpropagation to solve this problem in artificial neural networks.

辛顿博士推广了一种称为反向传播的巧妙的数学算法来解决人工神经网络中的这个问题。

These artificial neural networks can use millions of connections to tackle difficult tasks like image recognition, speech recognition, and even language translation.

这些人工神经网络可以使用数百万个连接来处理图像识别、语音识别甚至语言翻译等困难任务。

Even with huge amounts of training, artificial neural networks trained in this way fall well short of human levels of performance.

即使经过大量的训练，以这种方式训练的人工神经网络仍然远远达不到人类的表现水平。

This is changing and neuroscience having moved on it is now known that artificial neural networks are fundamentally different from their biological counterparts, Dr.

这种情况正在发生变化，神经科学已经向前迈进，现在人们已经知道人工神经网络与它们的生物学对应物有着根本的不同，Dr.

Nicholas Sexton and Bradley Love, a pair of neuroscientists of University College London, started out rather sceptical about the supposed resemblance between natural and artificial neural networks.

伦敦大学学院的一对神经科学家尼古拉斯·塞克斯顿 (Nicholas Sexton) 和布拉德利·洛夫 (Bradley Love) 一开始对自然神经网络和人工神经网络之间假定的相似性持怀疑态度。

Another indication that the analogy between artificial neural networks and natural ones is useful is that the study of the former can make testable predictions about the latter.

人工神经网络与自然神经网络之间的类比有用的另一个迹象是，对前者的研究可以对后者做出可检验的预测。

His hope was that by developing artificial neural networks that could learn to solve complex problems, light might be shed on how the brain's neural networks do the same.

他希望通过开发能够学习解决复杂问题的人工神经网络，揭示大脑神经网络如何做到同样的事情。

When the authors tested out prospective configuration in artificial neural networks they found that they learned in a much more human-like way—more robustly and with less training—than models trained with backprop.

当作者测试人工神经网络中的前瞻性配置时，他们发现与使用反向传播训练的模型相比，它们的学习方式更像人类，而且更加稳健，所需训练更少。

This approach has driven rapid progress in computer vision, language translation and, most recently, the human-like conversational skills of chatbots such as GPT-4. The learning is done by software models called " artificial neural networks" (ANNs).

这种方法推动了计算机视觉、语言翻译以及最近聊天机器人（如 GPT-4）的类人对话技能的快速发展。学习是通过称为“人工神经网络”（ANN）的软件模型完成的。

If artificial neural networks can be given biologically realistic features, such as specialised neurons that can integrate activity and error signals in different parts of the cell, then backprop can occur with a single set of neurons.

如果人工神经网络能够具备生物学上的真实特征，比如能够整合细胞不同部分的活动和错误信号的专门神经元，那么反向传播就可以用一组神经元进行。