subfieldn. 子域；分栏；子字段；分支
artificial
intelligence (AI).
depiction:描绘
intuitively：adv. 直觉地，直观地；由直觉而得地
interchangeably：adv. 可交换地，可交替地
incarnations;n. 赋予形体( incarnation的名词复数 )；体现；前身；典型
prominent:adj. 突出的，杰出的；突起的；著名的
Venn diagram:韦恩图
mimic：模仿
a binary classifier;二进制分类器
that the weights used to determine the class label for a given input needed to be
manually tuned by a human – this type of model clearly does not scale well if a human operator is
required to intervene.用于确定给定输入的类标签的权重需要由人手动调整-如果需要人工操作员干预，这种类型的模型显然不能很好地缩放。
Perceptron-based techniques were all the rage in the neural network
community.:基于感知器的技术在神经网络中风靡一时。
stagnated:v. 停滞，不流动，不发展( stagnate的过去式和过去分词 )
demonstrated:v. 举行*（或集会）( demonstrate的过去式和过去分词 )；示范。展示；显示；论证
canonical:adj. 权威的；见于<圣经>正经篇目的；大教堂教士的；按照教规的
backpropagation:n. 反向传播(B-P)，可以用来表示一种神经网络算法，例如：B-P网络。
feedforward:前馈
approximators：近似器
cornerstone：n. 基石，基础；最重要的部分
computationally infeasible.计算上是不可行的。
incarnation:n. 化身；前身；典型体现
hierarchical:adj. 按等级划分的，等级（制度）的；分层的
quintessential:adj. 精髓的；典型的
handwritten character recognition: [计] 手写字符识别
sequentially:adv. 继续地，从而
hand-engineered:手工设计的
, we used hand-engineered features to quantify the contents of an image – we
rarely used raw pixel intensities as inputs to our machine learning models,，我们使用手工设计的特征来量化图像的内容——我们很少使用原始像素强度作为机器学习模型的输入，
we performed feature extraction我们进行了特征提取
a feature extractor or
image descriptor特征提取器或图像描述符
raw pixel intensities:原始像素强度
depicts:v. 描绘，描画( depict的第三人称单数 )；描述
Histogram of Oriented Gradients (:定向梯度直方图(HOG)
we try to understand the problem in terms of a hierarchy of concepts.我们试图从概念的层次结构来理解这个问题。
This hierarchical learning allows us to completely remove the hand-designed
feature extraction process and treat CNNs as end-to-end learners.这种分层学习允许我们完全删除手工设计的特征提取过程，并将CNN作为端到端的学习者。
only edge-like regions are detected in the lower level layers of
the network. These edge regions are used to define corners (where edges intersect) and contours
(outlines of objects). Combining corners and contours can lead to abstract “object parts” in the next layer.:在网络的下层层中只检测到边缘状区域。 这些边缘区域用于定义角（边相交的地方)和轮廓(物体的轮廓）。 结合角和轮廓可以导致抽象的“对象部分”在下一层。
Again, keep in mind that the types of concepts these filters are learning to detect are automatically learned – there is no intervention by us in the learning process.
再次，请记住，这些过滤器正在学习检测的概念的类型是自动学习的-在学习过程中没有我们的干预。
no consensus amongst experts:专家之间没有达成共识
Deep learning approach of stacking layers on top of each other that automatically learn
more complex, abstract, and discriminating features.深度学习方法，将层叠在彼此之上，自动学习更复杂、抽象和识别的特征。
where he discussed why the previous incarnations of deeplearning (ANNs) did not take off during the 1990s phase:Our labeled datasets were thousands of times too small.在那里，他讨论了为什么以前的深度学习(ANN)化身没有在1990年代阶段起飞：1。 我们标记的数据集是太小的数千倍
buzzwords surrounding deep learning:围绕深度学习的流行语
but each of these
schools of thought centralize around artificial neural networks inspired by the structure and
function of the brain. Regardless of network depth, width, or specialized network architecture,
you’re still performing machine learning using artificial neural networks.:但这些思想流派都集中在人工神经网络上，这些神经网络受到大脑结构和功能的启发。 无论网络深度、宽度或专门的网络体系结构如何，您仍然使用人工神经网络进行机器学习。