“A Global Geometric Framework for Nonlinear Dimensionality Reduction”. SCIENCE, Vol. 290, Dec. 2000. “一种用于非线性降维的全局几何框架”
“Here we describe an approach to solving dimensionality reduction problems that uses easily measured local metric information to learn the underlying global geometry of a data set.”
Isomap (Isometric Feature Mapping)Isomap (等距特征映射)
“我们在此描述一种解决降维问题的方法，使用 易测的局部度量信息来学习数据集潜在的全局几 何结构。”
“Nonlinear Dimensionality Reduction by Locally Linear Embedding”. SCIENCE, Vol. 290, Dec. 2000. “通过局部线性嵌入进行非线性降维”
“Here, we introduce locally linear embedding (LLE), an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs.”
“这里，我们提出局部线性嵌入(LLE)，一种计 算高维输入数据中低维、邻域保护嵌入的非监 督学习算法。”
“Reducing the Dimensionality of Data with Neural Networks”. SCIENCE, Vol. 313, Jul. 2006. “利用神经元网络降低数据的维度”
“We describe an effective way of initializing the weights that allows deep autoencoder
networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.”
code: http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html
“我们描述一种初始化权重的有效方法，可让深 度自编码网络学习低维代码，作为一种降低数据 维度的工具，远远好于主成分分析方法。”
“Clustering by fast search and find of density peaks”. SCIENCE, Vol. 344, Jun. 2014. “通过快速查找和发现密度峰值进行聚类”
“We propose an approach based on the idea that cluster centers are characterized by a
higher density than their neighbors and by a relatively large distance from points with higher densities.”
“我们提出一种基于如下思想的方法：聚类中心 点具有密度高于相邻点、距离相对大于次高密度 点的特性。”
“Human-level concept learning through probabilistic program induction”. SCIENCE, Vol. 350, Dec. 2015. “凭借概率规划归纳法进行人类层级的概念学习
“We see the one-shot learning capacities studied here as a challenge for these neural
models: one we expect they might rise to by incorporating the principles of compositionality, causality, and learning to learnthat BPL instantiates.”
“我们看到本文研究的一次性学习能力作为对那些神 经模型的一种挑战：通过将组合性、因果性和学会学习 BPL实例化的原则相结合，成为一个我们期待它们会崛 起的方向。” “Human-level control through deep reinforcement learning”. NATURE, Vol. 518, Feb. 2015. “凭借深度强化学习达到人类水平的操控”
“Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning.”
“这里我们采用训练深度网络的最新进展开发一种新 颖的人造智能体，称为深度Q网络，应用端到端的强化 学习，能直接从高维感知输入中学习成功的策略。” “Deep learning”. NATURE, Vol. 521, May. 2015. “深度学习”
“Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. ” “深度学习通过利用反向传播算法发现大型数据集中 复杂的结构表明，一台机器如何改变其内部参数被用 于从前一层表征中计算出每层的表征。”
“Mastering the game of Go with deep neural networks and tree search”. NATURE, Vol. 529, Jan. 2016. “利用深度神经网络和树搜索征服围棋游戏”
Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. … Without any look ahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play.
“我们在此提出一种计算机围棋的新方法，使用‘价值网络’ 评价棋盘位置、使用‘策略网络’选择走子。… 没有任何前 向搜索，该神经网络以先进水平的蒙特卡洛树搜索程序博弈围 棋，模拟成千上万次随机自我对弈。”
What does it feel like to stand here?
It seems like a pretty intense place to be standing — but then you have to remember
something about what it’s like to stand on a time graph: you can’t see what’s to your right. 站在看起来好像是令人非常紧张的地方——然后你要记住站 在时间曲线上是什么感觉：你看不到你的右侧是什么。
o So here’s how it actually feels to stand there: which probably feels pretty normal… 而这里是要站立的实际感觉如何的地方：大概感觉相当平常 …
AI的分类可分为4种：类人思考, 理性思考, 类人动作和理性动作。
AI的8个基础学科包括：哲学、数学、经济学、神经科学、心理学、计算机工程、控制理论和控制论和语言学。
AI的3种类型：弱人工智能、强人工智能以及超人工智能。
人工智能
